# tau-bench-airline benchmark

| \# | model | tau-bench-airline | $/task | card | cheapest list | cheapest effective | unit | providers | tokens/week |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | `openai/gpt-5.1` | 80.0 | 0.3931 | 1.25 | 0.625 openai/flex | 0.2471 openai/flex |  | 2 | 999470698 |
| 2 | `anthropic/claude-fable-5` | 79.4 | 0.8491 | 10.0 | 10.0 azure | 3.27 anthropic |  | 5 | 1799948098 |
| 3 | `inclusionai/ling-3.1-flash` | 79.3 | 0.0315 |  | 0.045 deepinfra/fp4 | 0.0186 novita |  | 2 | 2465499085 |
| 4 | `anthropic/claude-fable-5.1` | 79.2 | 0.7162 | 10.0 | 10.0 amazon-bedrock | 2.1435 anthropic |  | 4 | 7573541962 |
| 5 | `anthropic/claude-sonnet-5.5` | 78.8 | 0.1593 | 2.0 | 2.0 amazon-bedrock | 0.3958 google-vertex/us |  | 5 | 90350909445 |
| 6 | `google/gemini-4-argon` | 78.7 | 0.4983 |  | 1.0 google-ai-studio/flex | 0.4977 google-ai-studio/flex |  | 2 | 33357280151 |
| 7 | `anthropic/claude-opus-5` | 78.7 | 0.473 | 5.0 | 5.0 azure/global | 1.1673 anthropic |  | 5 | 9999518143 |
| 8 | `qwen/qwen3.5-397b-a17b` | 78.5 | 0.201 |  | 0.39 alibaba | 0.3199 deepinfra/fp8 |  | 11 | 511195664 |
| 9 | `google/gemini-3.5-flash-lite` | 78.3 | 0.0744 |  | 0.15 google-ai-studio/flex | 0.093 google-vertex/global/flex |  | 2 | 8815470911 |
| 10 | `google/gemini-3.7-flash` | 78.3 | 0.1499 |  | 0.375 google-vertex/global/flex | 0.1294 google-ai-studio/flex |  | 2 | 16485676436 |
| 11 | `xiaomi/mimo-v2.6-flash` | 77.9 | 0.0148 | 0.14 | 0.1 io-net/fp8 | 0.011 gmicloud/bf16 |  | 9 | 188589602106 |
| 12 | `qwen/qwen3.5-122b-a10b` | 77.7 | 0.17 |  | 0.26 alibaba | 0.2597 siliconflow/fp8 |  | 5 | 456557296 |
| 13 | `qwen/qwen3.8-27b` | 77.5 | 0.0659 |  | 0.035 darkbloom/fp4 | 0.0103 chutes/fp8 |  | 26 | 38376372463 |
| 14 | `deepseek/deepseek-v4-pro-0813` | 77.5 | 0.101 | 1.32 | 0.0999 relace/fp4 | 0.0998 relace/fp4 |  | 24 | 38297722212 |
| 15 | `stepfun/step-3.7-flash` | 77.3 | 0.0201 | 0.2 | 0.16 deepinfra | 0.0456 deepinfra |  | 3 | 750713750 |
| 16 | `z-ai/glm-5.3` | 77.3 | 0.057 | 1.4 | 0.0699 wafer/us | 0.069 wafer/us |  | 39 | 244459012685 |
| 17 | `qwen/qwen3.6-27b` | 77.2 | 0.1446 |  | 0.25 chutes/fp8 | 0.1004 chutes/fp8 |  | 10 | 1018016186 |
| 18 | `deepseek/deepseek-v4-pro` | 77.2 | 0.0585 | 0.66 | 0.66 deepseek | 0.1881 streamlake/fp8 |  | 21 | 58724115254 |
| 19 | `google/gemini-3.1-pro-preview` | 77.0 | 0.3513 |  | 1.0 google-ai-studio/flex | 0.6497 google-ai-studio/flex |  | 2 | 4366256457 |
| 20 | `nvidia/nemotron-3-ultra-550b-a55b` | 76.9 | 0.1003 |  | 0.4 deepinfra/fp4/flex | 0.1215 deepinfra/fp4/flex |  | 5 | 3907102956 |
| 21 | `anthropic/claude-opus-4.8` | 76.8 | 0.4929 | 5.0 | 5.0 azure/global | 1.1933 amazon-bedrock |  | 5 | 7736756673 |
| 22 | `xiaomi/mimo-v2.6-pro` | 76.8 | 0.0684 | 0.435 | 0.3262 gmicloud/bf16 | 0.0284 gmicloud/bf16 |  | 5 | 33262750560 |
| 23 | `amazon/nova-micro-v1` | 76.7 | 1.275 |  | 0.035 amazon-bedrock/eu-west-1 | 0.0347 amazon-bedrock/eu-west-1 |  | 1 | 753428554 |
| 24 | `anthropic/claude-opus-4.7` | 76.4 | 0.4243 | 5.0 | 5.0 google-vertex/global | 1.5151 anthropic |  | 5 | 874219417 |
| 25 | `anthropic/claude-opus-4.5` | 76.3 | 0.5366 | 5.0 | 5.0 anthropic/2 | 3.6279 anthropic |  | 5 | 219516097 |
| 26 | `tencent/hy4-preview` | 76.0 | 0.1144 | 0.834 | 0.834 atlas-cloud/fp8 | 0.0646 tencent/fp8 |  | 6 | 6944527610 |
| 27 | `moonshotai/kimi-k3.1-pro` | 75.7 | 0.178 | 2.0 | 0.304 relace/fp4 | 0.2079 relace/fp4 |  | 17 | 127045171781 |
| 28 | `meta/muse-spark-open` | 75.7 | 0.0884 |  | 1.25 baseten/fp4 | 0.2765 makora/fp4 |  | 5 | 3455713072 |
| 29 | `qwen/qwen3.5-35b-a3b` | 75.6 | 0.0796 |  | 0.065 darkbloom/fp4 | 0.065 darkbloom/fp4 |  | 9 | 1631869476 |
| 30 | `z-ai/glm-5.3-flash` | 75.6 | 0.0087 | 0.15 | 0.0399 relace/fp4 | 0.0204 primeintellect |  | 40 | 806116523144 |
| 31 | `x-ai/grok-4.6` | 75.3 | 0.3309 | 2.0 | 2.0 xai/zdr | 0.7725 amazon-bedrock/us-west-2 |  | 2 | 2750565342 |
| 32 | `google/gemini-3.6-flash` | 75.3 | 0.1697 |  | 0.375 google-ai-studio/flex | 0.3217 google-ai-studio/flex |  | 2 | 3715265581 |
| 33 | `anthropic/claude-opus-5.5` | 75.3 | 0.3395 | 4.0 | 4.0 azure/global | 0.3991 google-vertex/europe |  | 5 | 265225848809 |
| 34 | `google/gemma-4-31b-it` | 75.3 | 0.0298 |  | 0.08 open-inference/bf16 | 0.0798 open-inference/bf16 |  | 22 | 24673261769 |
| 35 | `x-ai/grok-4.7` | 75.3 | 0.2932 | 2.0 | 2.0 amazon-bedrock/global | 0.6736 xai/zdr |  | 2 | 21521368346 |
| 36 | `openai/gpt-5.3-codex` | 75.3 | 0.2997 | 1.75 | 1.75 azure | 0.3165 azure |  | 2 | 457071536 |
| 37 | `deepseek/deepseek-v4.1-flash` | 75.1 | 0.033 | 0.15 | 0.006 relace/fp4 | 0.0048 primeintellect |  | 32 | 831323377790 |
| 38 | `anthropic/claude-sonnet-5` | 75.1 | 0.2006 | 2.0 | 2.0 amazon-bedrock/global | 0.3115 google-vertex/us |  | 5 | 19785018514 |
| 39 | `openai/gpt-5.4` | 75.0 | 0.2913 | 2.5 | 1.25 openai/flex | 0.9545 openai |  | 3 | 1559911228 |
| 40 | `qwen/qwen3.8-2.4t-a95b` | 74.8 | 0.1909 |  | 2.0 alibaba | 0.3546 together |  | 9 | 3375846448 |
| 41 | `deepseek/deepseek-v4-flash-vision-exp` | 74.8 | 0.0302 | 0.44 | 0.2156 deepinfra/fp8 | 0.0254 gmicloud/fp8 |  | 7 | 19162881398 |
| 42 | `meta/muse-glimmer-30b` | 74.7 | 0.0374 |  | 0.3 deepinfra/bf16 | 0.0604 phala |  | 5 | 1024965298 |
| 43 | `minimax/minimax-m3` | 74.5 | 0.026 | 0.3 | 0.224 deepinfra/fp8/flex | 0.0623 gmicloud/fp8 |  | 14 | 42355642611 |
| 44 | `anthropic/claude-opus-4.6` | 74.5 | 0.5068 | 5.0 | 5.0 google-vertex/global | 1.5218 anthropic |  | 5 | 4491236099 |
| 45 | `z-ai/glm-5` | 74.4 | 0.0447 | 1.0 | 0.6 streamlake/fp8 | 0.2836 z-ai/fp8 |  | 11 | 1644894669 |
| 46 | `deepseek/deepseek-v3.2` | 74.3 | 0.0416 |  | 0.2088 gmicloud/fp8 | 0.0926 gmicloud/fp8 |  | 15 | 29736505094 |
| 47 | `anthropic/claude-sonnet-4.6` | 74.1 | 0.3298 | 3.0 | 3.0 google-vertex/global | 1.072 amazon-bedrock/global |  | 5 | 9270256352 |
| 48 | `xiaomi/mimo-v2.5-pro` | 74.0 | 0.0293 | 0.435 | 0.3045 gmicloud/bf16 | 0.0612 xiaomi/fp8 |  | 7 | 17728731871 |
| 49 | `deepseek/deepseek-v4-flash-0731` | 73.9 | 0.0091 | 0.44 | 0.03 open-inference/fp4 | 0.0139 streamlake/fp8 |  | 37 | 314513489706 |
| 50 | `moonshotai/kimi-k2.7-code` | 73.8 | 0.0789 | 0.95 | 0.6 coreweave/int4 | 0.2388 coreweave/int4 |  | 18 | 1525673246 |
| 51 | `openai/gpt-5.5` | 73.7 | 0.477 | 5.0 | 2.5 openai/flex | 0.9605 openai/flex |  | 3 | 2430328494 |
| 52 | `moonshotai/kimi-k2.6` | 73.7 | 0.0638 | 0.95 | 0.39 chutes/int4 | 0.2277 chutes/int4 |  | 22 | 4176548547 |
| 53 | `moonshotai/kimi-k3` | 73.6 | 0.2603 | 3.0 | 0.153 wafer/fast | 0.1521 wafer/fast |  | 22 | 59504210550 |
| 54 | `deepseek/deepseek-v4-flash` | 73.5 | 0.0114 | 0.22 | 0.05 relace/fp4 | 0.0203 open-inference/fp8 |  | 24 | 264245760211 |
| 55 | `openai/gpt-5.6-sol` | 73.3 | 0.1269 | 4.0 | 2.0 openai/flex | 1.2602 azure/us |  | 3 | 10412992133 |
| 56 | `google/gemini-3-flash-preview` | 73.3 | 0.1237 |  | 0.25 google-ai-studio/flex | 0.0928 google-ai-studio/flex |  | 2 | 22369124012 |
| 57 | `openai/gpt-5.2` | 73.3 | 0.2413 | 1.75 | 0.875 openai/flex | 0.6736 openai/flex |  | 2 | 1003013452 |
| 58 | `deepseek/deepseek-v3.1-terminus` | 73.0 | 0.0629 |  | 0.27 deepinfra/fp4 | 0.2037 atlas-cloud/fp8 |  | 5 | 823280489 |
| 59 | `xiaomi/mimo-v2.5` | 72.9 | 0.01 | 0.14 | 0.119 gmicloud/fp8 | 0.0126 xiaomi/fp8 |  | 7 | 490191247748 |
| 60 | `nvidia/nemotron-3.5-super-vl` | 72.9 | 0.0331 |  | 0.06 darkbloom/nvfp4 | 0.0344 primeintellect/nvfp4 |  | 10 | 18683979833 |
| 61 | `qwen/qwen3.5-9b` | 72.9 | 0.0333 |  | 0.053 primeintellect/bf16 | 0.0787 darkbloom/fp4 |  | 7 | 3637842369 |
| 62 | `anthropic/claude-haiku-5.5` | 72.8 | 0.0116 | 0.1 | 0.1 anthropic | 0.0425 azure/global |  | 5 | 139788290103 |
| 63 | `openai/gpt-6-astra-pro` | 72.7 | 2.9136 | 10.0 | 5.0 openai/flex | 1.4761 openai/flex |  | 2 | 1273455495 |
| 64 | `google/gemini-3.5-flash` | 72.7 | 0.4317 |  | 0.75 google-ai-studio/flex | 0.2479 google-ai-studio/flex |  | 2 | 1763021737 |
| 65 | `anthropic/claude-sonnet-4.5` | 72.5 | 0.3287 | 3.0 | 3.0 google-vertex/global | 0.6022 google-vertex/us-east5 |  | 5 | 2446063053 |
| 66 | `openai/gpt-5.6-terra` | 72.3 | 0.1113 | 2.0 | 1.0 openai/flex | 0.4604 azure |  | 3 | 4625799877 |
| 67 | `deepseek/deepseek-v4.1-flash-1017` | 72.3 | 0.0292 | 0.3 | 0.006 relace/fp4 | 0.0045 deepinfra/fp8/flex |  | 41 | 2701423607321 |
| 68 | `qwen/qwen3.6-35b-a3b` | 72.3 | 0.0415 |  | 0.018 primeintellect/fp8 | 0.0127 primeintellect/fp8 |  | 12 | 9059542464 |
| 69 | `z-ai/glm-4.6` | 72.1 | 0.0527 | 0.6 | 0.4 deepinfra/fp4/flex | 0.163 venice/fp4 |  | 5 | 854974071 |
| 70 | `qwen/qwen3.7-max` | 72.0 | 0.4029 |  | 1.475 alibaba | 0.6225 alibaba |  | 1 | 229410698 |
| 71 | `z-ai/glm-5.1` | 71.9 | 0.0973 | 1.4 | 0.9 chutes/fp8 | 0.3379 chutes/fp8 |  | 18 | 1682206009 |
| 72 | `z-ai/glm-4.7` | 71.8 | 0.0597 | 0.6 | 0.32 deepinfra/fp4/flex | 0.2166 deepinfra/fp4/flex |  | 9 | 1793109277 |
| 73 | `openai/gpt-5-mini` | 71.7 | 0.128 | 0.25 | 0.125 openai/flex | 0.0405 openai/flex |  | 2 | 2841429611 |
| 74 | `z-ai/glm-5.2` | 71.5 | 0.0469 | 1.4 | 0.0066 relace/fp4 | 0.0062 wafer/us |  | 34 | 67682870933 |
| 75 | `qwen/qwen3.8-flash` | 71.3 | 0.0167 |  | 0.15 alibaba | 0.0322 alibaba |  | 2 | 45074568765 |
| 76 | `google/gemini-3.1-flash-lite` | 71.3 | 0.0801 |  | 0.125 google-vertex/global/flex | 0.0667 google-vertex/eu |  | 2 | 17408115717 |
| 77 | `google/gemini-3.8-flash` | 71.3 | 0.2102 |  | 0.375 google-vertex/global/flex | 0.1745 google-ai-studio/flex |  | 2 | 66105151093 |
| 78 | `minimax/minimax-m2.7` | 70.9 | 0.027 | 0.3 | 0.21 gmicloud/fp8 | 0.0903 deepinfra/fp8 |  | 9 | 4062222361 |
| 79 | `z-ai/glm-4.5-air` | 70.9 | 0.0138 | 0.2 | 0.13 novita/bf16 | 0.0762 novita/bf16 |  | 3 | 106946576 |
| 80 | `inclusionai/ling-3.0-flash-fin` | 70.7 | 0.0048 |  | 0.06 deepinfra/fp4 | 0.0169 deepinfra/fp4 |  | 1 | 264897851 |
| 81 | `openai/gpt-5.6-sol-pro` | 70.7 | 0.7118 | 4.0 | 2.0 openai/flex | 1.4685 openai |  | 2 | 695188392 |
| 82 | `openai/gpt-5.6-luna-pro` | 70.3 | 0.0853 | 0.2 | 0.1 openai/flex | 0.0654 openai/flex |  | 2 | 3137471618 |
| 83 | `qwen/qwen3.7-plus` | 70.3 | 0.0543 |  | 0.32 alibaba | 0.1732 alibaba |  | 1 | 2491495658 |
| 84 | `anthropic/claude-sonnet-4` | 70.0 | 0.2977 |  | 3.0 amazon-bedrock | 1.4411 google-vertex/global |  | 2 | 1266922610 |
| 85 | `openai/gpt-6.1-sol` | 70.0 | 0.1013 | 2.0 | 1.0 openai/flex | 0.111 openai/flex |  | 3 | 120159205745 |
| 86 | `inclusionai/ling-3.0-flash-vl` | 70.0 | 0.003 |  | 0.06 deepinfra/fp16 | 0.028 deepinfra/fp16 |  | 1 | 144990235 |
| 87 | `moonshotai/kimi-k2.5` | 69.8 | 0.0536 | 0.6 | 0.45 deepinfra/fp4 | 0.1505 moonshotai/int4 |  | 10 | 1480447887 |
| 88 | `openai/gpt-5.6-luna` | 69.7 | 0.0132 | 0.2 | 0.1 openai/flex | 0.0591 openai/flex |  | 3 | 65706471235 |
| 89 | `reflection/beam-1.0-501b-a23b` | 69.3 | 0.0275 |  | 0.25 nebius/fp4 | 0.0612 together |  | 5 | 2111325689 |
| 90 | `openai/gpt-6-sol` | 69.3 | 0.13 | 2.0 | 1.0 openai/flex | 0.4568 openai/flex |  | 3 | 8857381915 |
| 91 | `moonshotai/kimi-k2-thinking` | 68.7 | 0.0446 |  | 0.6 google-vertex | 0.3613 novita/bf16 |  | 2 | 101424456 |
| 92 | `inclusionai/ling-3.0-flash` | 68.7 | 0.0022 |  | 0.021 novita | 0.0123 novita |  | 2 | 4782103295 |
| 93 | `google/gemma-4-26b-a4b-it` | 68.7 | 0.015 |  | 0.01 primeintellect/bf16 | 0.0104 primeintellect/bf16 |  | 15 | 17632526472 |
| 94 | `openai/gpt-6.1-terra` | 68.4 | 0.0636 | 1.0 | 0.5 openai/flex | 0.0589 openai/flex |  | 3 | 44362382979 |
| 95 | `openai/gpt-6-astra` | 68.0 | 0.5802 | 10.0 | 5.0 openai/flex | 1.0295 openai/flex |  | 3 | 12764530937 |
| 96 | `deepseek/deepseek-v3.2-exp` | 67.8 | 0.0563 |  | 0.27 atlas-cloud/fp8 | 0.2699 atlas-cloud/fp8 |  | 3 | 1057454921 |
| 97 | `openai/gpt-5` | 67.3 | 0.6292 | 1.25 | 1.25 azure | 0.7591 openai/default |  | 2 | 311907360 |
| 98 | `z-ai/glm-4.7-flash` | 67.3 | 0.008 |  | 0.06 deepinfra/bf16 | 0.0279 deepinfra/bf16 |  | 4 | 503434086 |
| 99 | `openai/gpt-5.2-chat` | 67.3 | 0.1116 |  | 1.75 azure |  |  | 1 |  |
| 100 | `openai/gpt-6-luna` | 67.3 | 0.0093 | 0.1 | 0.05 openai/flex | 0.0307 azure |  | 3 | 307311562986 |
| 101 | `thinkingmachines/inkling` | 67.2 | 0.0796 |  | 0.95 deepinfra/fp8 | 0.6663 together |  | 3 | 4073704634 |
| 102 | `openai/gpt-6-luna-pro` | 66.7 | 0.0388 | 0.1 | 0.05 openai/flex | 0.0201 openai/flex |  | 2 | 20728381439 |
| 103 | `minimax/minimax-m3.1-flash` | 66.7 | 0.0132 | 0.15 | 0.1125 gmicloud/fp8 | 0.0186 gmicloud/fp8 |  | 12 | 165405568604 |
| 104 | `openai/gpt-5.4-mini` | 66.7 | 0.0889 | 0.75 | 0.375 openai/flex | 0.0599 openai/flex |  | 2 | 3592057033 |
| 105 | `minimax/minimax-m2.1` | 66.6 | 0.0147 | 0.3 | 0.3 minimax/fp8 | 0.0952 minimax/fp8 |  | 2 | 300923844 |
| 106 | `minimax/minimax-m2.5` | 66.4 | 0.0221 | 0.3 | 0.22 inceptron/fp8 | 0.0452 siliconflow/fp8 |  | 11 | 2024556517 |
| 107 | `anthropic/claude-haiku-4.5` | 66.2 | 0.116 | 1.0 | 1.0 azure/global | 0.2325 amazon-bedrock/eu-west-1 |  | 4 | 5580791996 |
| 108 | `nvidia/nemotron-3.5-lightning` | 65.6 | 0.0169 |  | 0.025 darkbloom/int4 | 0.0175 darkbloom/int4 |  | 8 | 947152601 |
| 109 | `openai/gpt-oss-120b` | 65.4 | 0.011 |  | 0.03 akashml/fp4 | 0.0204 near-ai/fp4 |  | 24 | 16824607232 |
| 110 | `openai/gpt-5.4-nano` | 64.7 | 0.0296 | 0.2 | 0.1 openai/flex | 0.0491 openai/flex |  | 2 | 2347263828 |
| 111 | `qwen/qwen3-235b-a22b-thinking-2507` | 61.3 | 0.1227 |  | 0.23 alibaba | 0.2299 alibaba |  | 4 | 251351864 |
| 112 | `z-ai/glm-4.6v` | 60.7 | 0.0321 | 0.3 | 0.3 novita/bf16 | 0.2266 z-ai/fp8 |  | 2 | 79610746 |
| 113 | `thinkingmachines/inkling-small` | 60.7 | 0.0465 |  | 0.45 deepinfra/fp8 | 0.1244 baseten/fp8 |  | 3 | 646710202 |
| 114 | `qwen/qwen3-coder-next` | 60.5 | 0.047 |  | 0.12 parasail/bf16 | 0.0733 parasail/bf16 |  | 4 | 1276802354 |
| 115 | `ibm-granite/granite-4.2-8b` | 58.3 | 0.0153 |  | 0.06 coreweave/bf16 | 0.0212 coreweave/bf16 |  | 2 | 92131414 |
| 116 | `google/gemini-2.5-pro` | 58.0 | 0.2064 |  | 0.625 google-ai-studio/flex | 0.2859 google-ai-studio/flex |  | 2 | 4353720545 |
| 117 | `google/gemini-2.5-flash` | 56.7 | 0.0289 |  | 0.15 google-ai-studio/flex | 0.0958 google-ai-studio/flex |  | 2 | 39453554708 |
| 118 | `moonshotai/kimi-k2-0905` | 55.3 | 0.113 |  | 0.6 novita/fp8 | 0.5999 novita/fp8 |  | 1 | 225119163 |
| 119 | `openai/gpt-oss-20b` | 53.5 | 0.0164 |  | 0.018 darkbloom/fp8 | 0.0152 darkbloom/fp8 |  | 15 | 5890505215 |
| 120 | `google/gemini-2.5-flash-lite` | 53.4 | 0.0116 |  | 0.05 google-ai-studio/flex | 0.0375 google-ai-studio/flex |  | 2 | 55259395661 |
| 121 | `nvidia/nemotron-3-nano-30b-a3b` | 52.0 | 0.0284 |  | 0.05 crusoe/fp8 | 0.0295 nebius/fp8 |  | 4 | 795814817 |
| 122 | `deepseek/deepseek-r1-0528` | 50.2 | 0.1647 |  | 0.5 deepinfra/fp4 | 0.4381 deepinfra/fp4 |  | 4 | 426276956 |
| 123 | `openai/gpt-5-nano` | 48.3 | 0.0406 | 0.05 | 0.025 openai/flex | 0.0169 openai/flex |  | 2 | 2151750077 |
| 124 | `qwen/qwen3-coder` | 48.0 | 0.0524 |  | 0.22 google-vertex/us-south1 | 0.0767 venice/fp8 |  | 5 | 595791409 |
| 125 | `google/gemma-3-12b-it` | 48.0 | 0.011 |  | 0.04 deepinfra/bf16/flex | 0.0394 deepinfra/bf16/flex |  | 2 | 348865025 |
| 126 | `openai/gpt-4.1` | 47.7 | 0.1256 | 2.0 | 2.0 azure | 1.2994 azure/swedencentral |  | 2 | 1682583922 |
| 127 | `qwen/qwen3-32b` | 47.1 | 0.0212 |  | 0.08 deepinfra/fp8 | 0.0795 deepinfra/fp8 |  | 5 | 1151022867 |
| 128 | `qwen/qwen3-30b-a3b` | 47.0 | 0.0355 |  | 0.12 deepinfra/fp8 | 0.1198 deepinfra/fp8 |  | 2 | 220782763 |
| 129 | `qwen/qwen3-next-80b-a3b-instruct` | 46.7 | 0.0238 |  | 0.072 deepinfra/fp8/flex | 0.0719 deepinfra/fp8/flex |  | 5 | 188711750 |
| 130 | `mistralai/mistral-small-2603` | 46.0 | 0.0112 | 0.15 | 0.15 mistral | 0.0662 mistral/zdr |  | 2 | 1133534667 |
| 131 | `deepseek/deepseek-chat-v3.1` | 46.0 | 0.0724 |  | 0.25 deepinfra/fp4 | 0.1968 deepinfra/fp4 |  | 8 | 3439868728 |
| 132 | `openai/gpt-4.1-mini` | 44.3 | 0.0232 | 0.4 | 0.4 azure | 0.2386 azure |  | 2 | 4293262180 |
| 133 | `qwen/qwen3-14b` | 44.0 | 0.0313 |  | 0.1 nextbit/int4 | 0.0994 nextbit/int4 |  | 3 | 100754729 |
| 134 | `deepseek/deepseek-chat-v3-0324` | 43.3 | 0.0776 |  | 0.24 deepinfra/fp4 | 0.2182 deepinfra/fp4 |  | 5 | 1547656279 |
| 135 | `meta-llama/llama-4-maverick` | 42.9 | 0.0572 |  | 0.1875 digitalocean | 0.1872 digitalocean |  | 5 | 1166480972 |
| 136 | `qwen/qwen3-coder-30b-a3b-instruct` | 42.7 | 0.0211 |  | 0.07 novita/fp8 | 0.0699 siliconflow/fp8 |  | 5 | 267638432 |
| 137 | `openai/gpt-4o-2024-08-06` | 42.7 | 0.2122 | 2.5 | 2.5 azure | 2.2318 azure |  | 2 | 48293294 |
| 138 | `openai/gpt-4o` | 41.7 | 0.1965 | 2.5 | 2.5 azure | 2.2567 openai |  | 2 | 531370864 |
| 139 | `qwen/qwen3-vl-235b-a22b-instruct` | 40.8 | 0.0751 |  | 0.2 deepinfra/fp8 | 0.145 parasail/fp8 |  | 5 | 1664163900 |
| 140 | `openai/gpt-4o-2024-05-13` | 40.0 | 1.1316 | 5.0 | 5.0 azure | 5.0 azure |  | 2 | 4475376 |
| 141 | `deepseek/deepseek-chat` | 39.8 | 0.069 |  | 0.256 deepinfra/fp4/flex | 0.2538 deepinfra/fp4/flex |  | 3 | 795313498 |
| 142 | `qwen/qwen3-235b-a22b-2507` | 39.2 | 0.0206 |  | 0.0875 gmicloud/fp8 | 0.0897 deepinfra/fp8 |  | 11 | 3006307426 |
| 143 | `qwen/qwen3-30b-a3b-instruct-2507` | 38.7 | 0.0252 |  | 0.0481 streamlake | 0.0479 streamlake |  | 6 | 2437832339 |
| 144 | `qwen/qwen3-vl-30b-a3b-instruct` | 35.3 | 0.0774 |  | 0.13 alibaba | 0.1291 alibaba |  | 4 | 445512644 |
| 145 | `meta-llama/llama-3.3-70b-instruct` | 33.0 | 0.0516 |  | 0.1 deepinfra/turbo | 0.0997 deepinfra/turbo |  | 12 | 1923672456 |
| 146 | `qwen/qwen3-vl-8b-instruct` | 32.7 | 0.0287 |  | 0.117 alibaba | 0.1167 alibaba |  | 2 | 511387540 |
| 147 | `openai/gpt-4o-mini` | 30.7 | 0.0178 | 0.15 | 0.15 azure | 0.1112 azure |  | 2 | 7411041954 |
| 148 | `qwen/qwen-2.5-72b-instruct` | 24.0 | 0.0733 |  | 0.36 deepinfra/fp8 | 0.3595 deepinfra/fp8 |  | 2 | 42330708 |
| 149 | `meta-llama/llama-3.1-8b-instruct` | 23.5 | 0.0046 |  | 0.02 deepinfra/fp8 | 0.0194 novita/fp8 |  | 5 | 1886655330 |
| 150 | `mistralai/mistral-nemo` | 18.7 | 0.0197 | 0.15 | 0.0166 io-net/fp16 | 0.0122 io-net/fp16 |  | 6 | 15261188711 |
| 151 | `qwen/qwen-2.5-7b-instruct` | 16.7 | 0.017 |  | 0.1 phala | 0.0996 phala |  | 2 | 343255240 |
| 152 | `openai/gpt-4.1-nano` | 11.0 | 0.0068 | 0.1 | 0.1 azure | 0.0628 azure/swedencentral |  | 2 | 5749479513 |