# agentic benchmark

| \# | model | agentic | $/task | card | cheapest list | cheapest effective | unit | providers | tokens/week |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | `anthropic/claude-fable-5.1` | 58.0 |  | 10.0 | 10.0 amazon-bedrock | 2.1435 anthropic |  | 4 | 7573541962 |
| 2 | `anthropic/claude-opus-5` | 56.5 |  | 5.0 | 5.0 azure/global | 1.1673 anthropic |  | 5 | 9999518143 |
| 3 | `qwen/qwen3.8-max-0902` | 56.0 |  |  | 2.0 alibaba | 0.3589 alibaba |  | 1 | 8757807556 |
| 4 | `meta/muse-spark-1.3` | 55.5 |  | 1.25 | 1.25 google-vertex/global | 0.3469 meta |  | 2 | 3333839173 |
| 5 | `z-ai/glm-5.3` | 53.4 |  | 1.4 | 0.0699 wafer/us | 0.069 wafer/us |  | 39 | 244459012685 |
| 6 | `x-ai/grok-4.6` | 53.4 |  | 2.0 | 2.0 xai/zdr | 0.7725 amazon-bedrock/us-west-2 |  | 2 | 2750565342 |
| 7 | `openai/gpt-6-astra` | 51.5 |  | 10.0 | 5.0 openai/flex | 1.0295 openai/flex |  | 3 | 12764530937 |
| 8 | `anthropic/claude-fable-5` | 51.0 |  | 10.0 | 10.0 azure | 3.27 anthropic |  | 5 | 1799948098 |
| 9 | `z-ai/glm-5.3-flash` | 50.9 |  | 0.15 | 0.0399 relace/fp4 | 0.0204 primeintellect |  | 40 | 806116523144 |
| 10 | `moonshotai/kimi-k3` | 50.6 |  | 3.0 | 0.153 wafer/fast | 0.1521 wafer/fast |  | 22 | 59504210550 |
| 11 | `openai/gpt-5.6-sol` | 50.5 |  | 4.0 | 2.0 openai/flex | 1.2602 azure/us |  | 3 | 10412992133 |
| 12 | `qwen/qwen3.8-2.4t-a95b` | 50.1 |  |  | 2.0 alibaba | 0.3546 together |  | 9 | 3375846448 |
| 13 | `qwen/qwen3.8-max` | 49.9 |  |  | 2.0 alibaba | 0.58 alibaba |  | 1 | 3118556904 |
| 14 | `deepseek/deepseek-v4-flash-vision-exp` | 47.5 |  | 0.44 | 0.2156 deepinfra/fp8 | 0.0254 gmicloud/fp8 |  | 7 | 19162881398 |
| 15 | `qwen/qwen3.8-27b` | 46.5 |  |  | 0.035 darkbloom/fp4 | 0.0103 chutes/fp8 |  | 26 | 38376372463 |
| 16 | `anthropic/claude-sonnet-5` | 44.3 |  | 2.0 | 2.0 amazon-bedrock/global | 0.3115 google-vertex/us |  | 5 | 19785018514 |
| 17 | `meta/muse-spark-1.2` | 44.0 |  | 1.25 | 1.25 meta | 0.7251 meta |  | 1 | 82335175 |
| 18 | `openai/gpt-5.6-terra` | 43.7 |  | 2.0 | 1.0 openai/flex | 0.4604 azure |  | 3 | 4625799877 |
| 19 | `openai/gpt-5.6-luna` | 42.7 |  | 0.2 | 0.1 openai/flex | 0.0591 openai/flex |  | 3 | 65706471235 |
| 20 | `anthropic/claude-opus-4.8` | 42.6 |  | 5.0 | 5.0 azure/global | 1.1933 amazon-bedrock |  | 5 | 7736756673 |
| 21 | `deepseek/deepseek-v4-pro-0813` | 42.3 |  | 1.32 | 0.0999 relace/fp4 | 0.0998 relace/fp4 |  | 24 | 38297722212 |
| 22 | `x-ai/grok-4.5` | 42.1 |  | 2.0 | 2.0 xai | 0.8273 xai/zdr |  | 1 | 2130481258 |
| 23 | `deepseek/deepseek-v4-flash-0731` | 41.7 |  | 0.44 | 0.03 open-inference/fp4 | 0.0139 streamlake/fp8 |  | 37 | 314513489706 |
| 24 | `google/gemini-3.8-flash` | 41.1 |  |  | 0.375 google-vertex/global/flex | 0.1745 google-ai-studio/flex |  | 2 | 66105151093 |
| 25 | `anthropic/claude-opus-4.7` | 39.5 |  | 5.0 | 5.0 google-vertex/global | 1.5151 anthropic |  | 5 | 874219417 |
| 26 | `z-ai/glm-5.2` | 39.4 |  | 1.4 | 0.0066 relace/fp4 | 0.0062 wafer/us |  | 34 | 67682870933 |
| 27 | `openai/gpt-5.5` | 37.3 |  | 5.0 | 2.5 openai/flex | 0.9605 openai/flex |  | 3 | 2430328494 |
| 28 | `google/gemini-3.7-flash` | 36.4 |  |  | 0.375 google-vertex/global/flex | 0.1294 google-ai-studio/flex |  | 2 | 16485676436 |
| 29 | `anthropic/claude-sonnet-4.6` | 33.1 |  | 3.0 | 3.0 google-vertex/global | 1.072 amazon-bedrock/global |  | 5 | 9270256352 |
| 30 | `google/gemini-3.6-flash` | 30.2 |  |  | 0.375 google-ai-studio/flex | 0.3217 google-ai-studio/flex |  | 2 | 3715265581 |
| 31 | `minimax/minimax-m3` | 29.5 |  | 0.3 | 0.224 deepinfra/fp8/flex | 0.0623 gmicloud/fp8 |  | 14 | 42355642611 |
| 32 | `inclusionai/ling-3.0-flash-vl` | 28.7 |  |  | 0.06 deepinfra/fp16 | 0.028 deepinfra/fp16 |  | 1 | 144990235 |
| 33 | `inclusionai/ling-3.0-flash-fin` | 27.9 |  |  | 0.06 deepinfra/fp4 | 0.0169 deepinfra/fp4 |  | 1 | 264897851 |
| 34 | `deepseek/deepseek-v4-flash` | 27.9 |  | 0.22 | 0.05 relace/fp4 | 0.0203 open-inference/fp8 |  | 24 | 264245760211 |
| 35 | `deepseek/deepseek-v4-pro` | 27.7 |  | 0.66 | 0.66 deepseek | 0.1881 streamlake/fp8 |  | 21 | 58724115254 |
| 36 | `meta/muse-spark-1.1` | 27.5 |  | 1.25 | 1.25 meta | 0.7307 meta |  | 1 | 132134718 |
| 37 | `google/gemini-3.5-flash` | 27.3 |  |  | 0.75 google-ai-studio/flex | 0.2479 google-ai-studio/flex |  | 2 | 1763021737 |
| 38 | `thinkingmachines/inkling` | 24.3 |  |  | 0.95 deepinfra/fp8 | 0.6663 together |  | 3 | 4073704634 |
| 39 | `tencent/hy3-preview` | 24.1 |  |  | 0.18 gmicloud/bf16 | 0.1198 gmicloud/bf16 |  | 1 | 106766376 |
| 40 | `z-ai/glm-5.1` | 23.9 |  | 1.4 | 0.9 chutes/fp8 | 0.3379 chutes/fp8 |  | 18 | 1682206009 |
| 41 | `nex-agi/nex-n2-pro` | 23.7 |  | 0.25 | 0.25 nex-agi/fp8 | 0.0398 nex-agi/fp8 |  | 2 | 42940716 |
| 42 | `thinkingmachines/inkling-small` | 23.5 |  |  | 0.45 deepinfra/fp8 | 0.1244 baseten/fp8 |  | 3 | 646710202 |
| 43 | `xiaomi/mimo-v2.5-pro` | 22.7 |  | 0.435 | 0.3045 gmicloud/bf16 | 0.0612 xiaomi/fp8 |  | 7 | 17728731871 |
| 44 | `qwen/qwen3.7-max` | 22.5 |  |  | 1.475 alibaba | 0.6225 alibaba |  | 1 | 229410698 |
| 45 | `moonshotai/kimi-k2.6` | 22.1 |  | 0.95 | 0.39 chutes/int4 | 0.2277 chutes/int4 |  | 22 | 4176548547 |
| 46 | `moonshotai/kimi-k2.7-code` | 21.0 |  | 0.95 | 0.6 coreweave/int4 | 0.2388 coreweave/int4 |  | 18 | 1525673246 |
| 47 | `nvidia/nemotron-3-ultra-550b-a55b` | 20.1 |  |  | 0.4 deepinfra/fp4/flex | 0.1215 deepinfra/fp4/flex |  | 5 | 3907102956 |
| 48 | `openai/gpt-5.4-mini` | 19.7 |  | 0.75 | 0.375 openai/flex | 0.0599 openai/flex |  | 2 | 3592057033 |
| 49 | `inclusionai/ling-3.0-flash` | 19.3 |  |  | 0.021 novita | 0.0123 novita |  | 2 | 4782103295 |
| 50 | `qwen/qwen3.6-27b` | 18.5 |  |  | 0.25 chutes/fp8 | 0.1004 chutes/fp8 |  | 10 | 1018016186 |
| 51 | `openai/gpt-5.4-nano` | 17.7 |  | 0.2 | 0.1 openai/flex | 0.0491 openai/flex |  | 2 | 2347263828 |
| 52 | `qwen/qwen3.7-plus` | 17.5 |  |  | 0.32 alibaba | 0.1732 alibaba |  | 1 | 2491495658 |
| 53 | `x-ai/grok-4.3` | 17.2 |  | 1.25 | 1.25 xai | 0.851 xai |  | 1 | 1701166249 |
| 54 | `xiaomi/mimo-v2.5` | 15.8 |  | 0.14 | 0.119 gmicloud/fp8 | 0.0126 xiaomi/fp8 |  | 7 | 490191247748 |
| 55 | `anthropic/claude-sonnet-4.5` | 15.8 |  | 3.0 | 3.0 google-vertex/global | 0.6022 google-vertex/us-east5 |  | 5 | 2446063053 |
| 56 | `minimax/minimax-m2.7` | 15.3 |  | 0.3 | 0.21 gmicloud/fp8 | 0.0903 deepinfra/fp8 |  | 9 | 4062222361 |
| 57 | `google/gemini-3.5-flash-lite` | 14.3 |  |  | 0.15 google-ai-studio/flex | 0.093 google-vertex/global/flex |  | 2 | 8815470911 |
| 58 | `meituan/longcat-2.0` | 14.0 |  |  | 0.3 atlas-cloud/fp8 | 0.0268 atlas-cloud/fp8 |  | 1 | 615430229 |
| 59 | `qwen/qwen3.6-35b-a3b` | 13.1 |  |  | 0.018 primeintellect/fp8 | 0.0127 primeintellect/fp8 |  | 12 | 9059542464 |
| 60 | `inclusionai/ring-2.6-1t` | 10.7 |  |  | 0.075 novita | 0.0367 novita |  | 1 | 453776586 |
| 61 | `openai/gpt-5-mini` | 8.9 |  | 0.25 | 0.125 openai/flex | 0.0405 openai/flex |  | 2 | 2841429611 |
| 62 | `meta/muse-glimmer-30b` | 8.5 |  |  | 0.3 deepinfra/bf16 | 0.0604 phala |  | 5 | 1024965298 |
| 63 | `qwen/qwen3.5-397b-a17b` | 8.3 |  |  | 0.39 alibaba | 0.3199 deepinfra/fp8 |  | 11 | 511195664 |
| 64 | `google/gemini-3.1-pro-preview` | 8.2 |  |  | 1.0 google-ai-studio/flex | 0.6497 google-ai-studio/flex |  | 2 | 4366256457 |
| 65 | `anthropic/claude-haiku-4.5` | 8.0 |  | 1.0 | 1.0 azure/global | 0.2325 amazon-bedrock/eu-west-1 |  | 4 | 5580791996 |
| 66 | `qwen/qwen3.5-122b-a10b` | 7.6 |  |  | 0.26 alibaba | 0.2597 siliconflow/fp8 |  | 5 | 456557296 |
| 67 | `mistralai/mistral-medium-3-5` | 7.0 |  | 1.5 | 1.5 mistral/zdr | 1.4999 mistral |  | 1 | 312198004 |
| 68 | `deepseek/deepseek-v3.1-terminus` | 6.8 |  |  | 0.27 deepinfra/fp4 | 0.2037 atlas-cloud/fp8 |  | 5 | 823280489 |
| 69 | `openai/gpt-oss-120b` | 6.2 |  |  | 0.03 akashml/fp4 | 0.0204 near-ai/fp4 |  | 24 | 16824607232 |
| 70 | `inclusionai/ling-3.0-tiny` | 4.4 |  |  | 0.015 antdigital/fp8 | 0.0073 antdigital/fp8 |  | 1 | 130377541 |
| 71 | `google/gemma-4-31b-it` | 4.2 |  |  | 0.08 open-inference/bf16 | 0.0798 open-inference/bf16 |  | 22 | 24673261769 |
| 72 | `cohere/command-a` | 3.6 |  | 2.5 | 2.5 cohere | 2.4997 cohere |  | 1 | 840473 |
| 73 | `nvidia/nemotron-3.5-lightning` | 3.5 |  |  | 0.025 darkbloom/int4 | 0.0175 darkbloom/int4 |  | 8 | 947152601 |
| 74 | `google/gemma-4-26b-a4b-it` | 2.9 |  |  | 0.01 primeintellect/bf16 | 0.0104 primeintellect/bf16 |  | 15 | 17632526472 |
| 75 | `mistralai/devstral-2512` | 2.3 |  | 0.4 | 0.4 mistral/eu | 0.051 mistral/eu |  | 1 | 265445382 |
| 76 | `mistralai/mistral-medium-3.1` | 1.9 |  | 0.4 | 0.4 mistral/zdr | 0.1838 mistral/zdr |  | 1 | 237746482 |
| 77 | `nvidia/nemotron-3-super-120b-a12b` | 1.7 |  |  | 0.075 deepinfra/bf16 | 0.075 deepinfra/bf16 |  | 5 | 340604995 |
| 78 | `inception/mercury-2` | 1.6 |  | 0.25 | 0.25 inception | 0.1713 inception |  | 1 | 146887169 |
| 79 | `google/gemini-3.1-flash-lite-preview` | 1.6 |  |  | 0.125 google-ai-studio/flex | 0.1205 google-ai-studio/flex |  | 1 | 3003730468 |
| 80 | `google/gemini-2.5-pro` | 1.6 |  |  | 0.625 google-ai-studio/flex | 0.2859 google-ai-studio/flex |  | 2 | 4353720545 |
| 81 | `upstage/solar-pro-3` | 1.4 |  | 0.15 | 0.15 upstage | 0.0758 upstage |  | 1 | 1838784 |
| 82 | `openai/gpt-oss-20b` | 1.4 |  |  | 0.018 darkbloom/fp8 | 0.0152 darkbloom/fp8 |  | 15 | 5890505215 |
| 83 | `ibm-granite/granite-4.2-8b` | 1.3 |  |  | 0.06 coreweave/bf16 | 0.0212 coreweave/bf16 |  | 2 | 92131414 |
| 84 | `qwen/qwen3-235b-a22b-thinking-2507` | 1.3 |  |  | 0.23 alibaba | 0.2299 alibaba |  | 4 | 251351864 |
| 85 | `qwen/qwen3.5-9b` | 1.2 |  |  | 0.053 primeintellect/bf16 | 0.0787 darkbloom/fp4 |  | 7 | 3637842369 |
| 86 | `deepseek/deepseek-r1` | 1.1 |  |  | 0.7 novita/fp8 | 0.6999 novita/fp8 |  | 2 | 133323311 |
| 87 | `mistralai/ministral-14b-2512` | 1.1 |  | 0.2 | 0.2 mistral | 0.1432 mistral/zdr |  | 1 | 295705464 |
| 88 | `arcee-ai/trinity-large-thinking` | 1.0 |  | 0.25 | 0.22 parasail/fp4 | 0.0515 arcee-ai |  | 2 | 121188704 |
| 89 | `cohere/command-a-plus` | 1.0 |  | 0.3 | 0.3 cohere/fp8 | 0.3 cohere/fp8 |  | 1 | 143605951 |
| 90 | `nvidia/nemotron-3-nano-30b-a3b` | 1.0 |  |  | 0.05 crusoe/fp8 | 0.0295 nebius/fp8 |  | 4 | 795814817 |
| 91 | `mistralai/mistral-large-2512` | 1.0 |  | 0.5 | 0.5 mistral/zdr | 0.2573 mistral/eu |  | 1 | 339999090 |
| 92 | `qwen/qwen3-30b-a3b-thinking-2507` | 0.9 |  |  | 0.2 alibaba | 0.1998 alibaba |  | 1 | 11499683 |
| 93 | `openai/o3-mini-high` | 0.9 |  | 1.1 | 1.1 openai | 1.0833 openai |  | 1 | 644912 |
| 94 | `qwen/qwen3-coder-next` | 0.9 |  |  | 0.12 parasail/bf16 | 0.0733 parasail/bf16 |  | 4 | 1276802354 |
| 95 | `qwen/qwen3-14b` | 0.9 |  |  | 0.1 nextbit/int4 | 0.0994 nextbit/int4 |  | 3 | 100754729 |
| 96 | `qwen/qwen3-32b` | 0.9 |  |  | 0.08 deepinfra/fp8 | 0.0795 deepinfra/fp8 |  | 5 | 1151022867 |
| 97 | `qwen/qwen3-8b` | 0.8 |  |  | 0.117 alibaba | 0.1168 alibaba |  | 1 | 227891339 |
| 98 | `mistralai/mistral-small-2603` | 0.8 |  | 0.15 | 0.15 mistral | 0.0662 mistral/zdr |  | 2 | 1133534667 |
| 99 | `mistralai/ministral-3b-2512` | 0.8 |  | 0.1 | 0.1 mistral/zdr | 0.0601 mistral/zdr |  | 1 | 303045039 |
| 100 | `deepseek/deepseek-chat-v3-0324` | 0.8 |  |  | 0.24 deepinfra/fp4 | 0.2182 deepinfra/fp4 |  | 5 | 1547656279 |
| 101 | `mistralai/ministral-8b-2512` | 0.6 |  | 0.15 | 0.15 mistral | 0.1121 mistral/zdr |  | 1 | 330838810 |
| 102 | `meta-llama/llama-4-maverick` | 0.6 |  |  | 0.1875 digitalocean | 0.1872 digitalocean |  | 5 | 1166480972 |
| 103 | `meta-llama/llama-4-scout` | 0.5 |  |  | 0.08 deepinfra/fp8/flex | 0.0797 deepinfra/fp8/flex |  | 4 | 553541000 |
| 104 | `google/gemma-3-12b-it` | 0.1 |  |  | 0.04 deepinfra/bf16/flex | 0.0394 deepinfra/bf16/flex |  | 2 | 348865025 |
| 105 | `google/gemma-3-27b-it` | 0.1 |  |  | 0.08 deepinfra/fp8 | 0.0623 parasail/fp8 |  | 6 | 1451898665 |