Anthropic: Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer u…
anthropic/claude-haiku-5.5-20261007
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.
It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 1000000
- Knowledge cutoff
- 2026-06
- Published model ID
- claude-haiku-5-5
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–14 / 14
86.902%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Claude Platform on AWS
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 7
- sample size
- 990
- 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
- Claude Platform on AWS
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:35:55.398Z
- 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
- 990
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8690236000000001
- accuracy_std_dev
- 0.0056741455250989255
- cost_per_task_usd
- 0.004051724242424242
- output_tokens_per_task
- 7872.538383838384
- latency_seconds_per_task
- 38.66653434343434
- 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
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗4.804%
- source id
- vercelAIGateway
- leaderboard name
- AI Gateway Text Requests Share
- dimension
- popularity
- metric
- Requests
- rank
- 7
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Claude Haiku 5.5
Original result ↗87.037%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Anthropic
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 10
- sample size
- 990
- 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
- Anthropic
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:14:20.331Z
- 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
- 990
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8703704
- accuracy_std_dev
- 0.00583193054142453
- cost_per_task_usd
- 0.004018268686868687
- output_tokens_per_task
- 7796.7444444444445
- latency_seconds_per_task
- 37.45491717171717
- 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
- 16
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗72.933%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Claude Platform on AWS
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 12
- 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
- Claude Platform on AWS
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:41:01.831Z
- 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
- 0.7293334
- accuracy_std_dev
- 0.026533159130416407
- cost_per_task_usd
- 0.012403696
- output_tokens_per_task
- 10764.472
- latency_seconds_per_task
- 92.314648
- 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
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗73.956%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Amazon Bedrock
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 14
- sample size
- 750
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 15
- 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
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:45:41.031Z
- 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
- 750
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7395555333333333
- accuracy_std_dev
- 0.016947170784004716
- cost_per_task_usd
- 0.013297554666666666
- output_tokens_per_task
- 10746.964
- latency_seconds_per_task
- 100.94712933333334
- 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
- 31
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗73.333%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Anthropic
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 14
- 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
- Anthropic
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T11:35:21.238Z
- 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
- 0.7333332
- accuracy_std_dev
- 0.032659904062320846
- cost_per_task_usd
- 0.012294704000000002
- output_tokens_per_task
- 10698.828
- latency_seconds_per_task
- 85.675876
- 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
- 16
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗73.133%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Azure
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 16
- 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
- Azure
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T11:19:23.393Z
- 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
- 0.7313332
- accuracy_std_dev
- 0.020231941744676914
- cost_per_task_usd
- 0.012560144
- output_tokens_per_task
- 10525.228
- latency_seconds_per_task
- 74.716332
- 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
- 40
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗86.756%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Google
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 17
- sample size
- 2970
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 15
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Google
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:38:41.553Z
- 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
- 2970
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8675645333333333
- accuracy_std_dev
- 0.00826267276262484
- cost_per_task_usd
- 0.004299042424242424
- output_tokens_per_task
- 7829.657575757576
- latency_seconds_per_task
- 36.21724208754209
- 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
- 40
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗73.6%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Google
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 19
- sample size
- 750
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 15
- 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
- Google
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T11:42:11.484Z
- 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
- 750
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7359999333333334
- accuracy_std_dev
- 0.0231964569463145
- cost_per_task_usd
- 0.013030309333333335
- output_tokens_per_task
- 10779.536
- latency_seconds_per_task
- 73.24675466666666
- 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
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗87.082%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 20
- sample size
- 2970
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 15
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Amazon Bedrock
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:49:45.152Z
- 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
- 2970
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8708191333333333
- accuracy_std_dev
- 0.005011630059061523
- cost_per_task_usd
- 0.004255378451178452
- output_tokens_per_task
- 7745.265656565656
- latency_seconds_per_task
- 39.48623198653199
- 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
- 32
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗86.717%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Azure
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 27
- sample size
- 1980
- 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
- Azure
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T09:34:38.477Z
- 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
- 1980
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8671716000000002
- accuracy_std_dev
- 0.006408346388890055
- cost_per_task_usd
- 0.0041782994949494945
- output_tokens_per_task
- 7724.74494949495
- latency_seconds_per_task
- 35.97794848484848
- 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
- 43
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗86.742%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · auto-routing
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 45
- sample size
- 792
- 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
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:27:45.642Z
- 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
- 792
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8674240000000001
- accuracy_std_dev
- 0.0048169925783625705
- cost_per_task_usd
- 0.004064253787878788
- output_tokens_per_task
- 7893.444444444444
- latency_seconds_per_task
- 38.62437373737374
- 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
- 132
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗72.833%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · auto-routing
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 53
- 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
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T12:31:32.731Z
- 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
- 0.72833325
- accuracy_std_dev
- 0.041197373838480274
- cost_per_task_usd
- 0.011627464999999998
- output_tokens_per_task
- 10669.235
- latency_seconds_per_task
- 86.46336500000001
- 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
- 128
- benchmark_evaluation
- true
- openrouter_permaslug
- anthropic/claude-haiku-5.5-20261007
- source model id
- anthropic/claude-haiku-5.5-20261007
Original result ↗36.5
- source id
- artificialAnalysis
- dimension
- intelligence
- metric
- Intelligence Index
Original result ↗Published prices
21–40 / 159
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.20
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_write_1h_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.13
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.10
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.50
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
- Billing conditions
- alias_target
- name
- Anthropic: Claude Haiku 5.5
- slug
- anthropic/claude-haiku-5.5
- routing_alias
- true
$0.05
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.06
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.63
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.13
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.69
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.14
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.10
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.55
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.11
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 100001
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- anthropic
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- anthropic | anthropic/claude-haiku-5.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 100001
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–4 / 4
- source model id
- anthropic/claude-haiku-5.5
- hosting
- third-party
- context length
- 1000000
- max output tokens
- 128000
- source model id
- anthropic/claude-haiku-5.5
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- azureml-anthropic/claude-haiku-5-5@1
- hosting
- foundry-managed-compute
- context length
- 1000000
- max output tokens
- 128000
- source model id
- azureml-anthropic/claude-haiku-5-5@2
- hosting
- foundry-managed-compute
- context length
- 1000000
- max output tokens
- 128000
Safety assessments
1–1 / 1
46 / 100
- source id
- stanfordFMTI
- canonical model id
- anthropic/claude-haiku-5.5-20261007
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Anthropic
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 46 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–16 / 16
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- June 2026
- normalized value
- 2026-06
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- June 2026
- normalized value
- 2026-06
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models