# 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 | 2.1238 anthropic |  | 4 | 7992736422 |
| 2 | `anthropic/claude-opus-5` | 56.5 |  | 5.0 | 5.0 amazon-bedrock | 1.1422 anthropic |  | 5 | 10866516566 |
| 3 | `qwen/qwen3.8-max-0902` | 56.0 |  |  | 2.0 alibaba/us-east-1 | 0.3595 alibaba |  | 1 | 9328705685 |
| 4 | `meta/muse-spark-1.3` | 55.5 |  | 1.25 | 1.25 google-vertex/global | 0.346 meta |  | 2 | 3405256128 |
| 5 | `z-ai/glm-5.3` | 53.4 |  | 1.4 | 0.0699 wafer/us | 0.069 wafer/us |  | 39 | 274701189780 |
| 6 | `x-ai/grok-4.6` | 53.4 |  | 2.0 | 2.0 xai/zdr | 0.7726 amazon-bedrock/us-west-2 |  | 2 | 2933970983 |
| 7 | `openai/gpt-6-astra` | 51.5 |  | 10.0 | 5.0 openai/flex | 1.0297 openai/flex |  | 3 | 14992636976 |
| 8 | `anthropic/claude-fable-5` | 51.0 |  | 10.0 | 10.0 azure | 3.0734 anthropic |  | 5 | 1985247563 |
| 9 | `z-ai/glm-5.3-flash` | 50.9 |  | 0.15 | 0.0399 relace/fp4 | 0.0202 primeintellect |  | 40 | 873359587942 |
| 10 | `moonshotai/kimi-k3` | 50.6 |  | 3.0 | 0.153 wafer/fast | 0.1517 wafer/us |  | 22 | 64194553722 |
| 11 | `openai/gpt-5.6-sol` | 50.5 |  | 4.0 | 2.0 openai/flex | 1.2191 amazon-bedrock/global |  | 3 | 11355341561 |
| 12 | `qwen/qwen3.8-2.4t-a95b` | 50.1 |  |  | 2.0 alibaba | 0.3546 together |  | 9 | 3434917488 |
| 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 | 0.026 gmicloud/fp8 |  | 7 | 19334675894 |
| 15 | `qwen/qwen3.8-27b` | 46.5 |  |  | 0.035 darkbloom/fp4 | 0.0104 chutes/fp8 |  | 26 | 40365538593 |
| 16 | `anthropic/claude-sonnet-5` | 44.3 |  | 2.0 | 2.0 azure/global | 0.3083 google-vertex/us |  | 5 | 21124505126 |
| 17 | `meta/muse-spark-1.2` | 44.0 |  | 1.25 | 1.25 meta | 0.7188 meta |  | 1 | 87653776 |
| 18 | `openai/gpt-5.6-terra` | 43.7 |  | 2.0 | 1.0 openai/flex | 0.3776 azure/eu |  | 3 | 5010008874 |
| 19 | `openai/gpt-5.6-luna` | 42.7 |  | 0.2 | 0.1 openai/flex | 0.0479 openai/flex |  | 3 | 70996018994 |
| 20 | `anthropic/claude-opus-4.8` | 42.6 |  | 5.0 | 5.0 azure/global | 1.1838 amazon-bedrock |  | 5 | 8174729253 |
| 21 | `deepseek/deepseek-v4-pro-0813` | 42.3 |  | 1.32 | 0.0999 relace/fp4 | 0.0998 relace/fp4 |  | 24 | 40426961697 |
| 22 | `x-ai/grok-4.5` | 42.1 |  | 2.0 | 2.0 xai | 0.8113 xai/zdr |  | 1 | 2337764706 |
| 23 | `deepseek/deepseek-v4-flash-0731` | 41.7 |  | 0.44 | 0.03 open-inference/fp4 | 0.0143 streamlake/fp8 |  | 37 | 328583524783 |
| 24 | `google/gemini-3.8-flash` | 41.1 |  |  | 0.375 google-ai-studio/flex | 0.1774 google-ai-studio/flex |  | 2 | 72268436836 |
| 25 | `anthropic/claude-opus-4.7` | 39.5 |  | 5.0 | 5.0 google-vertex/global | 1.4435 anthropic |  | 5 | 952286246 |
| 26 | `z-ai/glm-5.2` | 39.4 |  | 1.4 | 0.0066 relace/fp4 | 0.0062 wafer/us |  | 34 | 69415166061 |
| 27 | `openai/gpt-5.5` | 37.3 |  | 5.0 | 2.5 openai/flex | 0.9646 openai/flex |  | 3 | 2597779081 |
| 28 | `google/gemini-3.7-flash` | 36.4 |  |  | 0.375 google-vertex/global/flex | 0.1311 google-ai-studio/flex |  | 2 | 17644269641 |
| 29 | `anthropic/claude-sonnet-4.6` | 33.1 |  | 3.0 | 3.0 claude-on-aws | 1.103 amazon-bedrock/global |  | 5 | 9899031571 |
| 30 | `google/gemini-3.6-flash` | 30.2 |  |  | 0.375 google-ai-studio/flex | 0.3228 google-vertex/global/flex |  | 2 | 3921969355 |
| 31 | `minimax/minimax-m3` | 29.5 |  | 0.3 | 0.224 deepinfra/fp8/flex | 0.0617 gmicloud/fp8 |  | 14 | 44263895441 |
| 32 | `inclusionai/ling-3.0-flash-vl` | 28.7 |  |  | 0.06 deepinfra/fp16 | 0.0283 deepinfra/fp16 |  | 1 | 153265571 |
| 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 | 270400974317 |
| 35 | `deepseek/deepseek-v4-pro` | 27.7 |  | 0.66 | 0.66 deepseek | 0.1878 streamlake/fp8 |  | 21 | 60197337029 |
| 36 | `meta/muse-spark-1.1` | 27.5 |  | 1.25 | 1.25 meta | 0.7166 meta |  | 1 | 136778709 |
| 37 | `google/gemini-3.5-flash` | 27.3 |  |  | 0.75 google-vertex/global/flex | 0.2535 google-ai-studio/flex |  | 2 | 1886001122 |
| 38 | `thinkingmachines/inkling` | 24.3 |  |  | 0.95 deepinfra/fp8 | 0.6664 together |  | 3 | 4113949057 |
| 39 | `tencent/hy3-preview` | 24.1 |  |  | 0.18 gmicloud/bf16 | 0.1161 gmicloud/bf16 |  | 1 | 122736745 |
| 40 | `z-ai/glm-5.1` | 23.9 |  | 1.4 | 0.9 chutes/fp8 | 0.3486 chutes/fp8 |  | 18 | 1735166411 |
| 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 | 678682468 |
| 43 | `xiaomi/mimo-v2.5-pro` | 22.7 |  | 0.435 | 0.3045 gmicloud/bf16 | 0.0612 xiaomi/fp8 |  | 7 | 17780584423 |
| 44 | `qwen/qwen3.7-max` | 22.5 |  |  | 1.475 alibaba | 0.6275 alibaba |  | 1 | 251246175 |
| 45 | `moonshotai/kimi-k2.6` | 22.1 |  | 0.95 | 0.39 chutes/int4 | 0.2278 chutes/int4 |  | 22 | 4493003118 |
| 46 | `moonshotai/kimi-k2.7-code` | 21.0 |  | 0.95 | 0.6 coreweave/int4 | 0.2417 coreweave/int4 |  | 18 | 1660619526 |
| 47 | `nvidia/nemotron-3-ultra-550b-a55b` | 20.1 |  |  | 0.4 deepinfra/fp4/flex | 0.1239 deepinfra/fp4/flex |  | 5 | 3953055525 |
| 48 | `openai/gpt-5.4-mini` | 19.7 |  | 0.75 | 0.375 openai/flex | 0.0616 openai/flex |  | 2 | 3872674407 |
| 49 | `inclusionai/ling-3.0-flash` | 19.3 |  |  | 0.021 novita | 0.0123 novita |  | 2 | 5208174048 |
| 50 | `qwen/qwen3.6-27b` | 18.5 |  |  | 0.25 chutes/fp8 | 0.0977 chutes/fp8 |  | 10 | 1073842171 |
| 51 | `openai/gpt-5.4-nano` | 17.7 |  | 0.2 | 0.1 openai/flex | 0.0492 openai/flex |  | 2 | 2557538989 |
| 52 | `qwen/qwen3.7-plus` | 17.5 |  |  | 0.32 alibaba | 0.1746 alibaba |  | 1 | 2661688770 |
| 53 | `x-ai/grok-4.3` | 17.2 |  | 1.25 | 1.25 xai/zdr | 0.8542 xai |  | 1 | 1834920557 |
| 54 | `xiaomi/mimo-v2.5` | 15.8 |  | 0.14 | 0.119 gmicloud/fp8 | 0.0126 xiaomi/fp8 |  | 7 | 490262194184 |
| 55 | `anthropic/claude-sonnet-4.5` | 15.8 |  | 3.0 | 3.0 google-vertex/global | 0.6023 google-vertex/us-east5 |  | 5 | 2575991988 |
| 56 | `minimax/minimax-m2.7` | 15.3 |  | 0.3 | 0.21 gmicloud/fp8 | 0.0903 deepinfra/fp8 |  | 9 | 4085828990 |
| 57 | `google/gemini-3.5-flash-lite` | 14.3 |  |  | 0.15 google-vertex/global/flex | 0.0898 google-vertex/global/flex |  | 2 | 9561684016 |
| 58 | `meituan/longcat-2.0` | 14.0 |  |  | 0.3 atlas-cloud/fp8 | 0.0253 atlas-cloud/fp8 |  | 1 | 711306631 |
| 59 | `qwen/qwen3.6-35b-a3b` | 13.1 |  |  | 0.012 primeintellect/fp8 | 0.0129 primeintellect/fp8 |  | 12 | 9648264246 |
| 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 | 0.0401 openai/flex |  | 2 | 3107895431 |
| 62 | `meta/muse-glimmer-30b` | 8.5 |  |  | 0.3 deepinfra/bf16 | 0.0604 phala |  | 5 | 1054845788 |
| 63 | `qwen/qwen3.5-397b-a17b` | 8.3 |  |  | 0.39 alibaba | 0.3211 deepinfra/fp8 |  | 11 | 523261160 |
| 64 | `google/gemini-3.1-pro-preview` | 8.2 |  |  | 1.0 google-ai-studio/flex | 0.6695 google-ai-studio/flex |  | 2 | 4767179642 |
| 65 | `anthropic/claude-haiku-4.5` | 8.0 |  | 1.0 | 1.0 azure/global | 0.2343 amazon-bedrock/eu-west-1 |  | 4 | 5892262965 |
| 66 | `qwen/qwen3.5-122b-a10b` | 7.6 |  |  | 0.26 alibaba | 0.2597 siliconflow/fp8 |  | 5 | 466370471 |
| 67 | `mistralai/mistral-medium-3-5` | 7.0 |  | 1.5 | 1.5 mistral | 1.4999 mistral |  | 1 | 353189640 |
| 68 | `deepseek/deepseek-v3.1-terminus` | 6.8 |  |  | 0.27 deepinfra/fp4 | 0.2037 atlas-cloud/fp8 |  | 5 | 856280682 |
| 69 | `openai/gpt-oss-120b` | 6.2 |  |  | 0.03 akashml/bf16 | 0.0204 near-ai/fp4 |  | 24 | 17933485366 |
| 70 | `inclusionai/ling-3.0-tiny` | 4.4 |  |  | 0.015 antdigital/fp8 | 0.0074 antdigital/fp8 |  | 1 | 142896612 |
| 71 | `google/gemma-4-31b-it` | 4.2 |  |  | 0.08 open-inference/bf16 | 0.0798 open-inference/bf16 |  | 22 | 25864564273 |
| 72 | `cohere/command-a` | 3.6 |  | 2.5 | 2.5 cohere | 2.4997 cohere |  | 1 | 869114 |
| 73 | `nvidia/nemotron-3.5-lightning` | 3.5 |  |  | 0.025 darkbloom/int4 | 0.0176 darkbloom/int4 |  | 8 | 980694613 |
| 74 | `google/gemma-4-26b-a4b-it` | 2.9 |  |  | 0.011 primeintellect/bf16 | 0.0103 primeintellect/bf16 |  | 15 | 18851505875 |
| 75 | `mistralai/devstral-2512` | 2.3 |  | 0.4 | 0.4 mistral/eu | 0.0518 mistral/eu |  | 1 | 272954132 |
| 76 | `mistralai/mistral-medium-3.1` | 1.9 |  | 0.4 | 0.4 mistral/zdr | 0.1931 mistral/zdr |  | 1 | 252285205 |
| 77 | `nvidia/nemotron-3-super-120b-a12b` | 1.7 |  |  | 0.075 deepinfra/bf16 | 0.0749 deepinfra/bf16 |  | 5 | 380251293 |
| 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 | 0.1204 google-ai-studio/flex |  | 1 | 3284485566 |
| 80 | `google/gemini-2.5-pro` | 1.6 |  |  | 0.625 google-ai-studio/flex | 0.2856 google-ai-studio/flex |  | 2 | 4433828948 |
| 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 | 0.0151 darkbloom/fp8 |  | 15 | 6275183458 |
| 83 | `ibm-granite/granite-4.2-8b` | 1.3 |  |  | 0.06 coreweave/bf16 | 0.0212 coreweave/bf16 |  | 2 | 97973447 |
| 84 | `qwen/qwen3-235b-a22b-thinking-2507` | 1.3 |  |  | 0.23 alibaba | 0.2299 alibaba |  | 4 | 251642422 |
| 85 | `qwen/qwen3.5-9b` | 1.2 |  |  | 0.071 primeintellect/bf16 | 0.0788 darkbloom/fp4 |  | 7 | 3885066827 |
| 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/zdr | 0.1479 mistral/zdr |  | 1 | 326998825 |
| 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 | 145538718 |
| 90 | `nvidia/nemotron-3-nano-30b-a3b` | 1.0 |  |  | 0.05 crusoe/fp8 | 0.0298 nebius/fp8 |  | 4 | 804580247 |
| 91 | `mistralai/mistral-large-2512` | 1.0 |  | 0.5 | 0.5 mistral | 0.2957 mistral/eu |  | 1 | 352277520 |
| 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 | 1333865408 |
| 95 | `qwen/qwen3-14b` | 0.9 |  |  | 0.1 nextbit/int4 | 0.0994 nextbit/int4 |  | 3 | 103920281 |
| 96 | `qwen/qwen3-32b` | 0.9 |  |  | 0.08 deepinfra/fp8 | 0.0795 deepinfra/fp8 |  | 5 | 1205817583 |
| 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 | 0.0682 mistral/zdr |  | 2 | 1178140212 |
| 99 | `mistralai/ministral-3b-2512` | 0.8 |  | 0.1 | 0.1 mistral | 0.06 mistral/zdr |  | 1 | 330618992 |
| 100 | `deepseek/deepseek-chat-v3-0324` | 0.8 |  |  | 0.24 deepinfra/fp4 | 0.2182 deepinfra/fp4 |  | 5 | 1615201051 |
| 101 | `mistralai/ministral-8b-2512` | 0.6 |  | 0.15 | 0.15 mistral | 0.1118 mistral/zdr |  | 1 | 334061910 |
| 102 | `meta-llama/llama-4-maverick` | 0.6 |  |  | 0.1875 digitalocean | 0.1872 digitalocean |  | 5 | 1191050987 |
| 103 | `meta-llama/llama-4-scout` | 0.5 |  |  | 0.08 deepinfra/fp8/flex | 0.0797 deepinfra/fp8/flex |  | 4 | 574737376 |
| 104 | `google/gemma-3-12b-it` | 0.1 |  |  | 0.04 deepinfra/bf16/flex | 0.0394 deepinfra/bf16/flex |  | 2 | 368254548 |
| 105 | `google/gemma-3-27b-it` | 0.1 |  |  | 0.08 deepinfra/fp8 | 0.0624 parasail/fp8 |  | 6 | 1528819788 |