DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on …
deepseek/deepseek-v4.1-flash-20260910
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental [V4 Flash Vision Exp](https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp).
It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds [V4 Pro](https://openrouter.ai/deepseek/deepseek-v4-pro-0813) on performance, speed, and task completion time.
Specifications & capabilities
- Input
- text, image
- Output
- text
- Context window · tokens
- 1048576
- Published model ID
- DeepSeek-V4.1-Flash
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗Evaluations
21–40 / 83
86.476%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Cohere
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 4
- sample size
- 594
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Cohere
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:15:03.392Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 594
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8647586666666667
- accuracy_std_dev
- 0.008943734131906087
- cost_per_task_usd
- 0.05048964983164983
- output_tokens_per_task
- 41902.75589225589
- latency_seconds_per_task
- 169.53773232323232
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 7
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗76.417%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · DigitalOcean
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 400
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 8
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- DigitalOcean
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:30:14.640Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 400
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7641665000000001
- accuracy_std_dev
- 0.021586383312171588
- cost_per_task_usd
- 0.0185151775
- output_tokens_per_task
- 14323.5575
- latency_seconds_per_task
- 270.0966575
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 20
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗75.47%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Baidu
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 248
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 5
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Baidu
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-10T18:13:04.202Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 248
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7547045887096774
- accuracy_std_dev
- 0.03743255869747622
- cost_per_task_usd
- 0.02217318548387097
- output_tokens_per_task
- 15344.233870967742
- latency_seconds_per_task
- 116.33360483870968
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 11
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗73.733%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Ionstream
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 250
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 5
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Ionstream
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-21T12:36:51.217Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 250
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7373334
- accuracy_std_dev
- 0.020482933819157834
- cost_per_task_usd
- 0.039714615999999994
- output_tokens_per_task
- 27822.08
- latency_seconds_per_task
- 174.77363200000002
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 5
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗72.444%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · River
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 150
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- River
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-14T23:10:29.432Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 150
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7244443333333334
- accuracy_std_dev
- 0.017708476037072058
- cost_per_task_usd
- 0.01403336
- output_tokens_per_task
- 21082.76
- latency_seconds_per_task
- 98.4962
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 5
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗90.277%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Novita
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1781
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 9
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Novita
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:31:10.643Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1781
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9027699539584503
- accuracy_std_dev
- 0.006295075818094274
- cost_per_task_usd
- 0.028251830432341377
- output_tokens_per_task
- 28841.043234138124
- latency_seconds_per_task
- 172.53925996631108
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 59
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗89.267%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · InferenceNet
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 2337
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 12
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- InferenceNet
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-04T21:06:11.704Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 2337
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8926684364569961
- accuracy_std_dev
- 0.021409854620919034
- cost_per_task_usd
- 0.01926024176294395
- output_tokens_per_task
- 30225.52802738554
- latency_seconds_per_task
- 249.78602053915276
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 10
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗88.565%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Sail Research
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1491
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 8
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Sail Research
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-24T09:01:43.485Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1491
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8856471629778674
- accuracy_std_dev
- 0.009013068317726206
- cost_per_task_usd
- 0.010023977867203217
- output_tokens_per_task
- 28220.264922870556
- latency_seconds_per_task
- 270.7399617706237
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 11
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗88.218%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · PrimeIntellect
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1184
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- PrimeIntellect
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:31:11.691Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1184
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8821789256756756
- accuracy_std_dev
- 0.01706691482241463
- cost_per_task_usd
- 0.04157157263513513
- output_tokens_per_task
- 34476.61317567567
- latency_seconds_per_task
- 164.1069873310811
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 22
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗88.103%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Crusoe
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1188
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Crusoe
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:47:44.999Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1188
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8810325
- accuracy_std_dev
- 0.016020429392393534
- cost_per_task_usd
- 0.03953295538720539
- output_tokens_per_task
- 32800.2398989899
- latency_seconds_per_task
- 203.57452356902357
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 15
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗87.598%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Decart
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1059
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Decart
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:15:03.294Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1059
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8759833172804533
- accuracy_std_dev
- 0.02383166285579381
- cost_per_task_usd
- 0.006660402266288952
- output_tokens_per_task
- 36610.579792256845
- latency_seconds_per_task
- 451.84041265344666
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 9
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗76%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · DekaLLM
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 150
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- DekaLLM
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-10T11:23:23.352Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 150
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.76
- accuracy_std_dev
- 0.014401594564491825
- cost_per_task_usd
- 0.019761673333333334
- output_tokens_per_task
- 17811.393333333333
- latency_seconds_per_task
- 291.19325333333336
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 10
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗75.733%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · NextBit
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 250
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 5
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- NextBit
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-03T08:55:31.322Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 250
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7573333999999999
- accuracy_std_dev
- 0.03991088294989224
- cost_per_task_usd
- 0.023026752
- output_tokens_per_task
- 18473.992
- latency_seconds_per_task
- 161.149652
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 8
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗74.583%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Decart
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 200
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 4
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Decart
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-24T12:31:49.408Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 200
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.74583325
- accuracy_std_dev
- 0.03402396010442498
- cost_per_task_usd
- 0.02499106
- output_tokens_per_task
- 52531.49
- latency_seconds_per_task
- 929.62778
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 9
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗72.833%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · PrimeIntellect
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 300
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 6
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- PrimeIntellect
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:19:28.999Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 300
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7283335
- accuracy_std_dev
- 0.024626886091898288
- cost_per_task_usd
- 0.04604961333333333
- output_tokens_per_task
- 26239.556666666667
- latency_seconds_per_task
- 118.63039
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 21
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗89.853%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · GMICloud
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 2178
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 11
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- GMICloud
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-10T06:04:30.952Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 2178
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8985305454545454
- accuracy_std_dev
- 0.018596178744147863
- cost_per_task_usd
- 0.023964589072543615
- output_tokens_per_task
- 27930.285583103763
- latency_seconds_per_task
- 168.61135950413225
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 26
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗88.006%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Modal
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 1580
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 8
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Modal
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T09:42:46.430Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1580
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8800631670886074
- accuracy_std_dev
- 0.006743341790240229
- cost_per_task_usd
- 0.033778830379746834
- output_tokens_per_task
- 27961.480379746834
- latency_seconds_per_task
- 152.0458943037975
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 11
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗87.405%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Makora
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 1973
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 10
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Makora
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:10:37.345Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 1973
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8740494840344654
- accuracy_std_dev
- 0.0038017229265163467
- cost_per_task_usd
- 0.04434169640141917
- output_tokens_per_task
- 38209.482513938165
- latency_seconds_per_task
- 202.1977790167258
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 12
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗83.979%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Io Net
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 594
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Io Net
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-01T17:44:47.331Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 594
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8397870000000001
- accuracy_std_dev
- 0.06305207943174174
- cost_per_task_usd
- 0.013501392255892255
- output_tokens_per_task
- 24293.242424242424
- latency_seconds_per_task
- 269.24517676767675
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 15
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗74.259%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Sail Research
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 6
- sample size
- 450
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 9
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Sail Research
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-24T12:29:34.092Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 450
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7425926666666667
- accuracy_std_dev
- 0.03165311687654157
- cost_per_task_usd
- 0.013586744444444443
- output_tokens_per_task
- 22693.746666666666
- latency_seconds_per_task
- 236.88698000000002
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 11
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4.1-flash-20260910
- source model id
- deepseek/deepseek-v4.1-flash-20260910
Original result ↗Published prices
1–20 / 96
$0.0042
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.14
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.42
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.0034
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.11
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.34
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.0030
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:off:14-24
- label
- 14:00 – 24:00(UTC)
- Billing label
- Cached input tokens (per 1M)
$0.01
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:on:0-14
- label
- 00:00 – 14:00(UTC)
- Billing label
- Cached input tokens (per 1M)
$0.15
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:off:14-24
- label
- 14:00 – 24:00(UTC)
- Billing label
- Input tokens (per 1M)
$0.30
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:on:0-14
- label
- 00:00 – 14:00(UTC)
- Billing label
- Input tokens (per 1M)
$0.60
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:off:14-24
- label
- 14:00 – 24:00(UTC)
- Billing label
- Output tokens (per 1M)
$1.20
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- tier
- peak:on:0-14
- label
- 00:00 – 14:00(UTC)
- Billing label
- Output tokens (per 1M)
$0.02
- Inference provider
- vercelAIGatewayCatalog
- Platform
- alibaba
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- alibaba | deepseek/deepseek-v4.1-flash
- model_type
- language
- peak_pricing
- windows
- end_minute_utc
- 840
- start_minute_utc
- 0
- multiplier
- 2
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.15
- Inference provider
- vercelAIGatewayCatalog
- Platform
- alibaba
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- alibaba | deepseek/deepseek-v4.1-flash
- model_type
- language
- peak_pricing
- windows
- end_minute_utc
- 840
- start_minute_utc
- 0
- multiplier
- 2
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.60
- Inference provider
- vercelAIGatewayCatalog
- Platform
- alibaba
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- alibaba | deepseek/deepseek-v4.1-flash
- model_type
- language
- peak_pricing
- windows
- end_minute_utc
- 840
- start_minute_utc
- 0
- multiplier
- 2
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- baseten
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- baseten | deepseek/deepseek-v4.1-flash
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- baseten
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- baseten | deepseek/deepseek-v4.1-flash
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.30
- Inference provider
- vercelAIGatewayCatalog
- Platform
- baseten
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- baseten | deepseek/deepseek-v4.1-flash
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.30
- Inference provider
- vercelAIGatewayCatalog
- Platform
- baseten
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- baseten | deepseek/deepseek-v4.1-flash
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- baseten
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- baseten | deepseek/deepseek-v4.1-flash
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–6 / 6
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4.1-flash@1
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4.1-flash@2
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- deepseek-ai/deepseek-v4.1-flash
- hosting
- nvidia-catalog
- context length
- 1048576
- source model id
- deepseek-ai/DeepSeek-V4.1-Flash
- hosting
- siliconflow-hosted
- max output tokens
- 393216
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- source model id
- deepseek/deepseek-v4.1-flash
- hosting
- vercel-gateway
- context length
- 1048576
- max output tokens
- 32768
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- source model id
- publishers/deepseek-ai/models/deepseek-v4.1@deepseek-v4.1-flash
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
32 / 100
- source id
- stanfordFMTI
- canonical model id
- deepseek/deepseek-v4.1-flash-20260910
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- DeepSeek
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 32 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–11 / 11
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- nvidiaNim
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1049K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 393216
- normalized value
- 393216
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 131072
- normalized value
- 131072
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 393K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- max_output_tokens
- value
- 32768
- normalized value
- 32768
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 1762074
- likes
- 4938
- pipeline tag
- image-text-to-text
- library name
- transformers
- License
- mit
Explore more models