Anthropic: Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels …
anthropic/claude-sonnet-5-20260630
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 1000000
- Knowledge cutoff
- 2026-01
- Published model ID
- claude-sonnet-5
- Capabilities
- batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
1–20 / 131
0.151
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Reliability Overall
- dimension
- general
- metric
- Arena score
- rank
- 1
- sample size
- 2691
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 0.1459797960264834
- confidence upper
- 0.15662480977103396
Original result ↗75.08%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Amazon Bedrock
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 8
- sample size
- 1450
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 29
- 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
- 2026-10-31T12:48:39.187Z
- 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
- 1450
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7508046206896551
- accuracy_std_dev
- 0.028089208249744292
- cost_per_task_usd
- 0.20928471310344823
- output_tokens_per_task
- 7693.8193103448275
- latency_seconds_per_task
- 114.15132896551724
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗74.533%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Claude Platform on AWS
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 8
- 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
- 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
- 2026-10-31T11:08:14.469Z
- 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
- 0.7453334
- accuracy_std_dev
- 0.019955555062187585
- cost_per_task_usd
- 0.19500222599999997
- output_tokens_per_task
- 7613.552
- latency_seconds_per_task
- 112.882412
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗0.074
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 9
- sample size
- 125181
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 0.06222692478266662
- confidence upper
- 0.08530815964382937
Original result ↗85.292%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Claude Platform on AWS
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 10
- 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
- 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
- 2026-10-31T08:45:37.246Z
- 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
- 0.8529231818181818
- accuracy_std_dev
- 0.050715229397844924
- cost_per_task_usd
- 0.16514445041322315
- output_tokens_per_task
- 16302.865472910928
- latency_seconds_per_task
- 163.85984297520662
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗74.8%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Anthropic
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 10
- 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
- Anthropic
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T11:28:40.153Z
- 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
- 0.7480001
- accuracy_std_dev
- 0.037333425000795194
- cost_per_task_usd
- 0.19706498
- output_tokens_per_task
- 7573.922
- latency_seconds_per_task
- 95.60386
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗1,447.273
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality German
- dimension
- factuality
- metric
- Arena rating
- rank
- 11
- sample size
- 381
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 1419.0806400564654
- confidence upper
- 1475.4662688236751
Original result ↗86.639%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Anthropic
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 11
- 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
- Anthropic
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-31T08:27:53.385Z
- 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
- 0.866391
- accuracy_std_dev
- 0.031399399620780255
- cost_per_task_usd
- 0.1546900968778696
- output_tokens_per_task
- 15252.516069788797
- latency_seconds_per_task
- 152.67489577594122
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗74.633%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Azure
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 12
- sample size
- 1000
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 20
- 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
- 2026-10-31T12:38:13.068Z
- 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
- 1000
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.74633335
- accuracy_std_dev
- 0.028478019009887265
- cost_per_task_usd
- 0.201189951
- output_tokens_per_task
- 7554.449
- latency_seconds_per_task
- 95.684807
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗74.533%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Google
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 15
- sample size
- 1500
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 30
- 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
- 2026-10-31T13:20:20.506Z
- 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
- 1500
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.7453333
- accuracy_std_dev
- 0.032313302845886877
- cost_per_task_usd
- 0.20589792800000006
- output_tokens_per_task
- 7426.582
- latency_seconds_per_task
- 90.84494666666667
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗86.45%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Google
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 18
- sample size
- 6534
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 33
- 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
- 2026-10-31T08:51:08.192Z
- 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
- 6534
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8645034242424242
- accuracy_std_dev
- 0.03391179125947315
- cost_per_task_usd
- 0.1657385367309458
- output_tokens_per_task
- 15317.695592286502
- latency_seconds_per_task
- 152.5027294153658
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗87.184%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Amazon Bedrock
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 19
- sample size
- 6138
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 31
- 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
- 2026-10-31T08:33:01.888Z
- 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
- 6138
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8718365483870967
- accuracy_std_dev
- 0.025673440848897774
- cost_per_task_usd
- 0.17548565819485176
- output_tokens_per_task
- 16263.557673509287
- latency_seconds_per_task
- 159.8330208536983
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗1,468.879
- source id
- lmarena
- leaderboard name
- LMArena Document Style Control Overall
- dimension
- productivity
- metric
- Arena rating
- rank
- 20
- sample size
- 11044
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 1462.2795160758783
- confidence upper
- 1475.4794730315189
Original result ↗0.028
- source id
- lmarena
- leaderboard name
- LMArena Agent Steerability Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 22
- sample size
- 10631
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 0.010481622594088795
- confidence upper
- 0.04472830328520617
Original result ↗0.02
- source id
- lmarena
- leaderboard name
- LMArena Agent Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 23
- sample size
- 41769
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 0.008041826624701688
- confidence upper
- 0.03195541934406931
Original result ↗1,459.54
- source id
- lmarena
- leaderboard name
- LMArena Document Overall
- dimension
- productivity
- metric
- Arena rating
- rank
- 24
- sample size
- 11044
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 1452.9723464032672
- confidence upper
- 1466.1069635082836
Original result ↗1,442.289
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Japanese
- dimension
- factuality
- metric
- Arena rating
- rank
- 24
- sample size
- 459
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 1418.4146603566453
- confidence upper
- 1466.1632269511933
Original result ↗87.221%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Azure
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 25
- sample size
- 4356
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 22
- 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
- 2026-10-31T08:57:30.925Z
- 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
- 4356
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8722068181818181
- accuracy_std_dev
- 0.028274856431813575
- cost_per_task_usd
- 0.16051083654729112
- output_tokens_per_task
- 15411.82598714417
- latency_seconds_per_task
- 154.4574214876033
- 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-sonnet-5-20260630
- source model id
- anthropic/claude-sonnet-5-20260630
Original result ↗-0.012
- source id
- lmarena
- leaderboard name
- LMArena Agent Praise Complaint Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 28
- sample size
- 6949
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- -0.0480088166222208
- confidence upper
- 0.02379582715014196
Original result ↗1,310.046
- source id
- lmarena
- leaderboard name
- LMArena Vision Homework
- dimension
- multimodal
- metric
- Arena rating
- rank
- 29
- sample size
- 1631
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Claude Sonnet 5 (High)
- confidence lower
- 1294.9462871413434
- confidence upper
- 1325.1464792250335
Original result ↗Published prices
41–60 / 82
$2.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- specific
- geo_region
- eu
- provider_region
- eu-central-1
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$10.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$11.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- specific
- geo_region
- au
- provider_region
- ap-southeast-2
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$11.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- specific
- geo_region
- eu
- provider_region
- eu-central-1
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$11.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- scope
- zone
- geo_region
- us
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- bedrock | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- claudeaws
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- claudeaws | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$2.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- claudeaws
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- claudeaws | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$2.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- claudeaws
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- claudeaws | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$10.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- claudeaws
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- claudeaws | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- claudeaws
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- claudeaws | anthropic/claude-sonnet-5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- au
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- eu
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.22
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$2.50
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$2.75
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- au
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$2.75
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- eu
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$2.75
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- region
- us
- model_type
- language
- quote_scope
- gateway_catalog
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–8 / 8
- source model id
- anthropic.claude-sonnet-5
- hosting
- bedrock-managed
- source model id
- anthropic/claude-sonnet-5
- hosting
- third-party
- context length
- 1000000
- max output tokens
- 128000
- source model id
- anthropic/claude-sonnet-5
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 128000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- azureml-anthropic/claude-sonnet-5@1
- hosting
- foundry-managed-compute
- context length
- 1000000
- max output tokens
- 128000
- source model id
- azureml-anthropic/claude-sonnet-5@2
- hosting
- foundry-managed-compute
- context length
- 1000000
- max output tokens
- 128000
- source model id
- claude-sonnet-5
- hosting
- gateway
- context length
- 1000000
- max output tokens
- 128000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- Claude Sonnet 5
- hosting
- copilot-subscription
- license
- CC-BY-4.0
- attribution
- GitHub and github/docs contributors
- plans
- max
- true
- pro
- true
- business
- true
- pro_plus
- true
- enterprise
- true
- clients
- vs
- true
- cli
- true
- xcode
- true
- dotcom
- true
- vscode
- true
- eclipse
- true
- jetbrains
- true
- auto selection
- app
- true
- cli
- true
- chat
- true
- cloud_agent
- true
- access scope
- Published plan/client flags; account settings, organization policy and additional access conditions apply
- availability
- supported
- release status
- GA
- billing scope
- Copilot subscription usage; not an unconditional inference API rate
- billing rates
- unit
- tokens_per_million
- input
- 2
- output
- 10
- currency
- USD
- original
- input
- $2.00
- model
- Claude Sonnet 5
- output
- $10.00
- category
- Versatile
- provider
- anthropic
- cache_write
- $2.50
- cached_input
- $0.20
- release_status
- GA
- cache_write
- 2.5
- cached_input
- 0.2
- footnote_restrictions
- false
- requires_subscription
- true
- comparison
- name
- Claude Sonnet 5
- excels_at
- Complex problem-solving challenges, sophisticated reasoning
- task_area
- General-purpose coding and agent tasks
- further_reading
- [Claude Sonnet 5 model card](https://www-cdn.anthropic.com/9e6a1044980d8c4ed85669faf9c2a8342e2e9f1e/Claude%20Sonnet%205%20System%20Card.pdf)
- source model id
- publishers/anthropic/models/claude-sonnet-5@default
- hosting
- vertex-managed
- max input tokens
- 1000000
- max output tokens
- 128000
- capabilities
- batch
- computerUse
- multimodal
- promptCaching
- toolCalling
- visionInput
- webSearch
Safety assessments
1–1 / 1
46 / 100
- source id
- stanfordFMTI
- canonical model id
- anthropic/claude-sonnet-5-20260630
- 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
1–17 / 17
- 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
- vercelAIGatewayCatalog
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2026-01-31
- normalized value
- 2026-01-31
- precision
- day
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_input_tokens
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vertexAI
- 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
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- vertexAI
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- January 2026
- normalized value
- 2026-01
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- January 2026
- normalized value
- 2026-01
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models