MiniMax: MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise …
minimax/minimax-m2.5-20260211
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 198000
- Published model ID
- MiniMax-M2.5
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
1–20 / 26
83.333%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Friendli
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 1
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Friendli
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T19:19:06.625Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8333335000000001
- accuracy_std_dev
- 0.0016835000000000044
- cost_per_task_usd
- 0.02674798484848485
- output_tokens_per_task
- 22257.11111111111
- latency_seconds_per_task
- 520.8498636363637
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 7
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗84.806%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Minimax
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 4
- 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
- Minimax
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T19:17:08.288Z
- 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
- 0.848064
- accuracy_std_dev
- 0.003834285135458768
- cost_per_task_usd
- 0.05505487626262626
- output_tokens_per_task
- 28115.5202020202
- latency_seconds_per_task
- 405.18676767676766
- 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
- 4
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗67.167%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Minimax
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 4
- 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
- Minimax
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T17:02:26.936Z
- 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
- 0.67166675
- accuracy_std_dev
- 0.012802094015726486
- cost_per_task_usd
- 0.035549775
- output_tokens_per_task
- 9811.9
- latency_seconds_per_task
- 154.518065
- 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
- 4
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗65.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Friendli
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 7
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- Friendli
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T16:14:58.314Z
- 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
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.6566665
- accuracy_std_dev
- 0.0033334999999999892
- cost_per_task_usd
- 0.029754
- output_tokens_per_task
- 11169.75
- latency_seconds_per_task
- 250.7655
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 7
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗84.6%
- source id
- openCompass
- leaderboard name
- GPQA-Diamond
- dimension
- general
- metric
- GPQA-Diamond
- rank
- 9
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- GPQA-Diamond
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗22.2%
- source id
- openCompass
- leaderboard name
- HLE
- dimension
- general
- metric
- HLE
- rank
- 9
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- HLE
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗73.3%
- source id
- openCompass
- leaderboard name
- Average
- dimension
- general
- metric
- Average
- rank
- 12
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- Average
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗91.1%
- source id
- openCompass
- leaderboard name
- IFEval
- dimension
- general
- metric
- IFEval
- rank
- 14
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- IFEval
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗83.923%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · DigitalOcean
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 16
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- DigitalOcean
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T18:16:26.161Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8392255000000001
- accuracy_std_dev
- 0.002525500000000014
- cost_per_task_usd
- 0.028252058080808082
- output_tokens_per_task
- 23440.575757575756
- latency_seconds_per_task
- 430.22037878787876
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗73.6%
- source id
- openCompass
- leaderboard name
- LiveCodeBenchV6
- dimension
- general
- metric
- LiveCodeBenchV6
- rank
- 16
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- LiveCodeBenchV6
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗83.754%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · SiliconFlow
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 17
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- 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
- 2026-08-29T18:16:39.840Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8375420000000001
- accuracy_std_dev
- 0.007576000000000027
- cost_per_task_usd
- 0.028651648989898987
- output_tokens_per_task
- 23687.20202020202
- latency_seconds_per_task
- 499.9306313131313
- 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
- 34
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗82.239%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · StreamLake
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 18
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- 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
- 2026-08-29T18:09:03.379Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8223905000000001
- accuracy_std_dev
- 0.019360500000000003
- cost_per_task_usd
- 0.023091813131313133
- output_tokens_per_task
- 21871.75
- latency_seconds_per_task
- 454.7449166666667
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗66.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · DigitalOcean
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 18
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- DigitalOcean
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T16:36:42.164Z
- 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
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.6666665
- accuracy_std_dev
- 0.006666499999999964
- cost_per_task_usd
- 0.02906171
- output_tokens_per_task
- 9968.3
- latency_seconds_per_task
- 246.29485
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 20
- benchmark_evaluation
- true
- openrouter_permaslug
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗66%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · SiliconFlow
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 20
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- 2026-08-29T16:50:17.446Z
- 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
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.66
- accuracy_std_dev
- 0.020000000000000018
- cost_per_task_usd
- 0.022123540000000004
- output_tokens_per_task
- 9442.58
- latency_seconds_per_task
- 232.1173
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗86.2%
- source id
- openCompass
- leaderboard name
- AIME2025
- dimension
- general
- metric
- AIME2025
- rank
- 22
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- AIME2025
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗60.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · StreamLake
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 22
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- 2026-08-29T16:17:15.093Z
- 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
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.6066665
- accuracy_std_dev
- 0.026666500000000037
- cost_per_task_usd
- 0.02093522
- output_tokens_per_task
- 9568.11
- latency_seconds_per_task
- 280.64576
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗84.091%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Novita
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 24
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- 2026-08-29T18:12:43.943Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.8409089999999999
- accuracy_std_dev
- 0.0008420000000000094
- cost_per_task_usd
- 0.025631659090909094
- output_tokens_per_task
- 21303.184343434343
- latency_seconds_per_task
- 236.13589141414144
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗62%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · AtlasCloud
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 24
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- 2026-08-29T16:13:54.380Z
- 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
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.62
- accuracy_std_dev
- 0.026666999999999996
- cost_per_task_usd
- 0.02806645
- output_tokens_per_task
- 9796.43
- latency_seconds_per_task
- 246.86407
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗81.7%
- source id
- openCompass
- leaderboard name
- MMLU-Pro
- dimension
- general
- metric
- MMLU-Pro
- rank
- 25
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- MMLU-Pro
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- MiniMax-M2.5
Original result ↗79.209%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · AtlasCloud
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 25
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- 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
- 2026-08-29T18:09:57.600Z
- 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
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.7920875
- accuracy_std_dev
- 0.007575500000000013
- cost_per_task_usd
- 0.02811962121212121
- output_tokens_per_task
- 23480.530303030304
- latency_seconds_per_task
- 464.4975707070707
- 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
- minimax/minimax-m2.5-20260211
- source model id
- minimax/minimax-m2.5-20260211
Original result ↗Published prices
1–13 / 13
$0.06
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.30
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$1.20
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.30
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- bedrock | minimax/minimax-m2.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- bedrock
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- bedrock | minimax/minimax-m2.5
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.03
- 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
$0.03
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.38
- 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
$0.38
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- cache_write_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Cache write / 1M
- Pricing via
- Vercel AI Gateway
$0.30
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_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
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$0.60
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_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
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.40
- Inference provider
- vercelAIGatewayCatalog
- Platform
- Vercel AI Gateway
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- model_type
- language
- quote_scope
- gateway_catalog
- service_tier
- fast
- billing_scope
- Vercel public catalog; endpoint prices may differ
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–10 / 10
- source model id
- HuggingFace/minimaxai-minimax-m2.5@1
- hosting
- foundry-managed-compute
- license
- modified-mit
- source model id
- HuggingFace/minimaxai-minimax-m2.5@2
- hosting
- foundry-managed-compute
- license
- modified-mit
- source model id
- HuggingFace/minimaxai-minimax-m2.5@3
- hosting
- foundry-managed-compute
- license
- modified-mit
- source model id
- HuggingFace/minimaxai-minimax-m2.5@4
- hosting
- foundry-managed-compute
- license
- modified-mit
- source model id
- HuggingFace/minimaxai-minimax-m2.5@5
- hosting
- foundry-managed-compute
- license
- modified-mit
- source model id
- MiniMaxAI/MiniMax-M2.5
- hosting
- siliconflow-hosted
- capabilities
- promptCaching
- structuredOutputs
- toolCalling
- source model id
- minimax.minimax-m2.5
- hosting
- bedrock-managed
- source model id
- minimax/minimax-m2.5
- hosting
- vercel-gateway
- context length
- 204800
- max output tokens
- 131000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- source model id
- publishers/hf-minimaxai/models/minimax-m2.5@001
- hosting
- vertex-self-deployed
- source model id
- publishers/minimaxai/models/minimax-m2@minimax-m2.5
- hosting
- vertex-self-deployed
Source specification observations
1–5 / 5
- field
- context_length
- value
- 198000
- normalized value
- 198000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 197K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- context_length
- value
- 204800
- normalized value
- 204800
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 176947
- normalized value
- 176947
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 131000
- normalized value
- 131000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 1134101
- likes
- 1530
- pipeline tag
- text-generation
- library name
- transformers
- License
- other
Explore more models