DeepSeek: DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workf…
deepseek/deepseek-v4-flash-20260731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 1048576
- Knowledge cutoff
- 2025-05
- Published model ID
- DeepSeek-V4-Flash-0731
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
21–40 / 77
90.157%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Baidu
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 4
- sample size
- 2257
- 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
- Baidu
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-10T18:29:20.621Z
- 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
- 2257
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9015653066016837
- accuracy_std_dev
- 0.007303971162529
- cost_per_task_usd
- 0.013315422241914046
- output_tokens_per_task
- 26073.0053167922
- latency_seconds_per_task
- 151.6460602569783
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗76.267%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · SiliconFlow
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 500
- 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
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- SiliconFlow
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T13:19:25.796Z
- 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
- 500
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7626665
- accuracy_std_dev
- 0.026025525932245826
- cost_per_task_usd
- 0.022020616000000003
- output_tokens_per_task
- 15706.274
- latency_seconds_per_task
- 287.03181800000004
- 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
- 28
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗76.167%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · GMICloud
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- sample size
- 600
- 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
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- 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
- 2026-11-10T06:15:38.651Z
- 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
- 600
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.76166675
- accuracy_std_dev
- 0.025404142635027726
- cost_per_task_usd
- 0.023970375
- output_tokens_per_task
- 16443.75
- latency_seconds_per_task
- 166.71051500000002
- 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
- 23
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗89.819%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Wafer
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 3762
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 19
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Wafer
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T09:24:59.899Z
- 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
- 3762
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8981922631578948
- accuracy_std_dev
- 0.013259923107827002
- cost_per_task_usd
- 0.007911754917597024
- output_tokens_per_task
- 24268.396331738437
- latency_seconds_per_task
- 156.3543657628921
- 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
- 13
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗89.507%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Relace
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 3148
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 16
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Relace
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-02T17:25:00.911Z
- 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
- 3148
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8950656277001271
- accuracy_std_dev
- 0.016150328135211358
- cost_per_task_usd
- 0.007430722681067345
- output_tokens_per_task
- 28431.650254129607
- latency_seconds_per_task
- 254.76092153748414
- 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
- 13
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗87.453%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Makora
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 1157
- 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
- Makora
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-09-26T08:53:59.525Z
- 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
- 1157
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8745317312013828
- accuracy_std_dev
- 0.011186512454241005
- cost_per_task_usd
- 0.0043274416594641305
- output_tokens_per_task
- 21870.51080380294
- latency_seconds_per_task
- 185.02852031114955
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗85.859%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Io Net
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 5
- sample size
- 198
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 1
- 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
- 2026-08-22T09:56:05.550Z
- 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
- 198
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.858586
- cost_per_task_usd
- 0.009637575757575758
- output_tokens_per_task
- 16318.166666666666
- latency_seconds_per_task
- 172.30871717171718
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗76.067%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · AtlasCloud
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 500
- 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
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- AtlasCloud
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:26:48.848Z
- 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
- 500
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7606666
- accuracy_std_dev
- 0.030470293002201318
- cost_per_task_usd
- 0.047939388
- output_tokens_per_task
- 19517.584
- latency_seconds_per_task
- 181.256216
- 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
- 29
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗75.636%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · StreamLake
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 550
- 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
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- StreamLake
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T13:22:04.008Z
- 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
- 550
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7563635454545454
- accuracy_std_dev
- 0.01641972318648099
- cost_per_task_usd
- 0.005844881818181818
- output_tokens_per_task
- 15989.905454545455
- latency_seconds_per_task
- 265.6822036363636
- 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
- 25
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗74.815%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Baidu
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- 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
- Baidu
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-10T18:35:45.854Z
- 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
- 0.7481482222222222
- accuracy_std_dev
- 0.02927572719953733
- cost_per_task_usd
- 0.012146982222222224
- output_tokens_per_task
- 16269.204444444444
- latency_seconds_per_task
- 103.90689555555556
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗74.815%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Io Net
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 45
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 1
- 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
- Io Net
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-22T08:32:23.660Z
- 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
- 45
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.748148
- cost_per_task_usd
- 0.021196088888888888
- output_tokens_per_task
- 8167.488888888889
- latency_seconds_per_task
- 92.10066666666667
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗74.274%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Morph
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 5
- sample size
- 195
- 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
- Morph
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-11-05T09:28:04.757Z
- 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
- 195
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7427351282051282
- accuracy_std_dev
- 0.028431218171008805
- cost_per_task_usd
- 0.013693692307692308
- output_tokens_per_task
- 18094.641025641027
- latency_seconds_per_task
- 1000.4725128205129
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗72.111%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · OpenInference
- 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
- OpenInference
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-17T10:32:07.729Z
- 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
- 0.7211110000000001
- accuracy_std_dev
- 0.04794518990124728
- cost_per_task_usd
- 0.011416513333333333
- output_tokens_per_task
- 25900.693333333333
- latency_seconds_per_task
- 885.57078
- 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
- 6
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗90.42%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Alibaba
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 3549
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 18
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Alibaba
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:28:13.141Z
- 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
- 3549
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.9041981924485772
- accuracy_std_dev
- 0.01113877499359892
- cost_per_task_usd
- 0.027435362073823615
- output_tokens_per_task
- 25932.813750352212
- latency_seconds_per_task
- 185.0526246830093
- 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
- 29
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗90.129%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Novita
- 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
- Novita
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:36:32.971Z
- 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
- 0.9012853636363636
- accuracy_std_dev
- 0.01164766215538338
- cost_per_task_usd
- 0.03467139577594123
- output_tokens_per_task
- 27670.98209366391
- latency_seconds_per_task
- 250.66662396694215
- 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-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗89.283%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Parasail
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 2171
- 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
- Parasail
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:16:11.302Z
- 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
- 2171
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8928297457392905
- accuracy_std_dev
- 0.010017422802463
- cost_per_task_usd
- 0.008073876554583142
- output_tokens_per_task
- 28391.647167204053
- latency_seconds_per_task
- 317.61189405803776
- 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
- 36
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗89.134%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · AtlasCloud
- 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
- AtlasCloud
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:53:51.020Z
- 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
- 0.8913374545454544
- accuracy_std_dev
- 0.018875016904814263
- cost_per_task_usd
- 0.0336423507805326
- output_tokens_per_task
- 25231.550505050505
- latency_seconds_per_task
- 191.3766694214876
- 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
- 30
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗88.935%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Cloudflare
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 2270
- 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
- Cloudflare
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:10:35.431Z
- 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
- 2270
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8893538140969164
- accuracy_std_dev
- 0.014720288133832686
- cost_per_task_usd
- 0.037593757268722466
- output_tokens_per_task
- 28197.38370044053
- latency_seconds_per_task
- 339.6227982378855
- 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
- 18
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗88.935%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Phala
- 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
- Phala
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T09:11:16.308Z
- 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
- 0.8893479090909092
- accuracy_std_dev
- 0.0107458728521871
- cost_per_task_usd
- 0.029853909090909094
- output_tokens_per_task
- 27657.61432506887
- latency_seconds_per_task
- 337.3929164370982
- 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
- 24
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗88.876%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Fireworks
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 6
- sample size
- 878
- 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
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Fireworks
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-09-19T08:54:58.652Z
- 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
- 878
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8887622653758542
- accuracy_std_dev
- 0.006290540123073671
- cost_per_task_usd
- 0.01762260478359909
- output_tokens_per_task
- 26459.921412300682
- latency_seconds_per_task
- 219.38370842824602
- 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
- 17
- benchmark_evaluation
- true
- openrouter_permaslug
- deepseek/deepseek-v4-flash-20260731
- source model id
- deepseek/deepseek-v4-flash-20260731
Original result ↗Published prices
1–20 / 68
$0.01
- Inference provider
- cloudflareWorkersAI
- Platform
- Cloudflare Workers AI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- per M cached input tokens
$1.32
- Inference provider
- cloudflareWorkersAI
- Platform
- Cloudflare Workers AI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- per M output tokens
$0.02
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.06
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.18
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.05
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.14
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.04
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- DeepSeek: DeepSeek V4 Flash 0731
- slug
- deepseek/deepseek-v4-flash-0731
- routing_alias
- true
$0.04
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- DeepSeek: DeepSeek V4 Flash 0731
- slug
- deepseek/deepseek-v4-flash-0731
- routing_alias
- true
$0.30
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- DeepSeek: DeepSeek V4 Flash 0731
- slug
- deepseek/deepseek-v4-flash-0731
- routing_alias
- true
$0.01
- 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)
$0.03
- 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)
$0.22
- 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)
$0.44
- 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)
$0.66
- 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)
$1.32
- 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-flash-0731
- 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
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- alibaba
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- alibaba | deepseek/deepseek-v4-flash-0731
- 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
$0.66
- Inference provider
- vercelAIGatewayCatalog
- Platform
- alibaba
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- alibaba | deepseek/deepseek-v4-flash-0731
- 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
Provider specifications & access
1–9 / 9
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4-flash-0731@1
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4-flash-0731@2
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4-flash-0731@3
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4-flash-0731@4
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- azure-huggingface/deepseek-ai--deepseek-v4-flash-0731@5
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 1048576
- source model id
- @cf/deepseek-ai/deepseek-v4-flash-0731
- hosting
- cloudflare-hosted
- context length
- 1048576
- source model id
- deepseek-ai/DeepSeek-V4-Flash-0731
- hosting
- siliconflow-hosted
- max output tokens
- 393216
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- source model id
- deepseek/deepseek-v4-flash-0731
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 384000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- source model id
- publishers/deepseek-ai/models/deepseek-v4@deepseek-v4-flash-0731
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
32 / 100
- source id
- stanfordFMTI
- canonical model id
- deepseek/deepseek-v4-flash-20260731
- 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
1–16 / 16
- 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
- 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
- azureFoundry
- 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
- 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
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-05
- normalized value
- 2025-05
- precision
- month
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 384000
- normalized value
- 384000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 384000
- normalized value
- 384000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- 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
- 384000
- normalized value
- 384000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 2577582
- likes
- 4099
- pipeline tag
- text-generation
- library name
- transformers
- License
- mit
Explore more models