Machine-readable data behind this page: /api/overview?dataset=fusaka&prompt=bare&refusals=fallback (JSON). How to query EthIQ: /llms.txt.
Ranked by pass rate. Filters: dataset=fusaka, prompt=bare, refusals=fallback. Questions in scope: 316. Models without full coverage of these questions are omitted unless include_partial=true.
| Rank | Model ID | Model | Lab | Effort | Prompt | Pass rate | 95% CI | Questions | Avg cost/question |
|---|---|---|---|---|---|---|---|---|---|
| 1 | gemini-4-argon-high | gemini-4-argon | high | bare | 88.6% | 84.6% to 91.7% | 316 | $0.0291 | |
| 2 | claude-fable-5-1-max | claude-fable-5-1 | anthropic | max | bare | 88.6% | 84.6% to 91.7% | 316 | $0.3262 |
| 3 | claude-opus-4.8-max | claude-opus-4.8 | anthropic | max | bare | 88.3% | 84.3% to 91.4% | 316 | $0.2849 |
| 4 | claude-sonnet-5-5-xhigh | claude-sonnet-5-5 | anthropic | xhigh | bare | 88.0% | 83.9% to 91.1% | 316 | $0.0693 |
| 5 | claude-opus-5-max | claude-opus-5 | anthropic | max | bare | 88.0% | 83.9% to 91.1% | 316 | $0.2071 |
| 6 | claude-fable-5-1-medium | claude-fable-5-1 | anthropic | medium | bare | 87.3% | 83.2% to 90.6% | 316 | $0.0536 |
| 7 | claude-fable-5-high | claude-fable-5 | anthropic | high | bare | 87.3% | 83.2% to 90.6% | 316 | $0.0874 |
| 8 | claude-opus-5-5-xhigh | claude-opus-5-5 | anthropic | xhigh | bare | 87.3% | 83.2% to 90.6% | 316 | $0.0999 |
| 9 | gpt-6.1-sol-max | gpt-6.1-sol | openai | max | bare | 87.3% | 83.2% to 90.6% | 316 | $0.0139 |
| 10 | gpt-6.1-terra-xhigh | gpt-6.1-terra | openai | xhigh | bare | 87.3% | 83.2% to 90.6% | 316 | $0.0025 |
| 11 | gpt-6-astra-max | gpt-6-astra | openai | max | bare | 87.1% | 82.9% to 90.3% | 316 | $0.0603 |
| 12 | gpt-6.1-sol-low | gpt-6.1-sol | openai | low | bare | 87.0% | 82.9% to 90.3% | 316 | $0.0026 |
| 13 | gpt-6-astra-low | gpt-6-astra | openai | low | bare | 87.0% | 82.9% to 90.3% | 316 | $0.0132 |
| 14 | gpt-6.1-sol-high | gpt-6.1-sol | openai | high | bare | 87.0% | 82.9% to 90.3% | 316 | $0.0048 |
| 15 | claude-fable-5-1-high | claude-fable-5-1 | anthropic | high | bare | 87.0% | 82.9% to 90.3% | 316 | $0.0693 |
| 16 | claude-fable-5-max | claude-fable-5 | anthropic | max | bare | 87.0% | 82.9% to 90.3% | 316 | $0.2691 |
| 17 | claude-fable-5-1-xhigh | claude-fable-5-1 | anthropic | xhigh | bare | 87.0% | 82.9% to 90.3% | 316 | $0.1458 |
| 18 | claude-fable-5-xhigh | claude-fable-5 | anthropic | xhigh | bare | 86.7% | 82.5% to 90.0% | 316 | $0.1246 |
| 19 | claude-opus-4.7-max | claude-opus-4.7 | anthropic | max | bare | 86.4% | 82.2% to 89.7% | 316 | $0.2365 |
| 20 | gpt-6.1-sol-medium | gpt-6.1-sol | openai | medium | bare | 86.4% | 82.2% to 89.7% | 316 | $0.0034 |
| 21 | gpt-6-astra-xhigh | gpt-6-astra | openai | xhigh | bare | 86.4% | 82.2% to 89.7% | 316 | $0.0412 |
| 22 | claude-sonnet-5-5-high | claude-sonnet-5-5 | anthropic | high | bare | 86.1% | 81.8% to 89.5% | 316 | $0.0356 |
| 23 | claude-opus-5-high | claude-opus-5 | anthropic | high | bare | 86.1% | 81.8% to 89.5% | 316 | $0.0590 |
| 24 | gpt-6.1-sol-xhigh | gpt-6.1-sol | openai | xhigh | bare | 85.8% | 81.5% to 89.2% | 316 | $0.0097 |
| 25 | claude-opus-5-xhigh | claude-opus-5 | anthropic | xhigh | bare | 85.4% | 81.1% to 88.9% | 316 | $0.1010 |
| 26 | claude-haiku-5-5-max | claude-haiku-5-5 | anthropic | max | bare | 85.4% | 81.1% to 88.9% | 316 | $0.0092 |
| 27 | claude-opus-4.8-high | claude-opus-4.8 | anthropic | high | bare | 85.4% | 81.1% to 88.9% | 316 | $0.0649 |
| 28 | claude-opus-4.8-xhigh | claude-opus-4.8 | anthropic | xhigh | bare | 85.4% | 81.1% to 88.9% | 316 | $0.1259 |
| 29 | claude-opus-4.7-xhigh | claude-opus-4.7 | anthropic | xhigh | bare | 85.1% | 80.8% to 88.6% | 316 | $0.0771 |
| 30 | claude-opus-5-medium | claude-opus-5 | anthropic | medium | bare | 84.8% | 80.4% to 88.3% | 316 | $0.0404 |
| 31 | gpt-5.6-sol-max | gpt-5.6-sol | openai | max | bare | 84.8% | 80.4% to 88.3% | 316 | $0.0743 |
| 32 | claude-fable-5-low | claude-fable-5 | anthropic | low | bare | 84.5% | 80.1% to 88.1% | 316 | $0.0343 |
| 33 | claude-haiku-5-5-high | claude-haiku-5-5 | anthropic | high | bare | 84.5% | 80.1% to 88.1% | 316 | $0.0014 |
| 34 | claude-haiku-5-5-xhigh | claude-haiku-5-5 | anthropic | xhigh | bare | 84.2% | 79.7% to 87.8% | 316 | $0.0023 |
| 35 | gpt-6.1-terra-high | gpt-6.1-terra | openai | high | bare | 84.2% | 79.7% to 87.8% | 316 | $0.0016 |
| 36 | gpt-6.1-terra-max | gpt-6.1-terra | openai | max | bare | 83.9% | 79.4% to 87.5% | 316 | $0.0134 |
| 37 | gpt-5.3-codex-xhigh | gpt-5.3-codex | openai | xhigh | bare | 83.9% | 79.4% to 87.5% | 316 | $0.1027 |
| 38 | claude-opus-4.8-medium | claude-opus-4.8 | anthropic | medium | bare | 83.5% | 79.1% to 87.2% | 316 | $0.0487 |
| 39 | claude-sonnet-5-5-medium | claude-sonnet-5-5 | anthropic | medium | bare | 83.5% | 79.1% to 87.2% | 316 | $0.0235 |
| 40 | claude-sonnet-5-5-low | claude-sonnet-5-5 | anthropic | low | bare | 82.9% | 78.4% to 86.7% | 316 | $0.0152 |
| 41 | gpt-5.6-sol-xhigh | gpt-5.6-sol | openai | xhigh | bare | 82.6% | 78.0% to 86.4% | 316 | $0.0442 |
| 42 | gemini-3.8-flash-high | gemini-3.8-flash | high | bare | 82.0% | 77.3% to 85.8% | 316 | $0.0607 | |
| 43 | gpt-5.4-xhigh | gpt-5.4 | openai | xhigh | bare | 82.0% | 77.3% to 85.8% | 316 | $0.0964 |
| 44 | gpt-6.1-terra-medium | gpt-6.1-terra | openai | medium | bare | 82.0% | 77.3% to 85.8% | 316 | $0.0013 |
| 45 | claude-opus-4.5-high | claude-opus-4.5 | anthropic | high | bare | 82.0% | 77.3% to 85.8% | 316 | $0.1529 |
| 46 | claude-opus-4.8-low | claude-opus-4.8 | anthropic | low | bare | 81.6% | 77.0% to 85.5% | 316 | $0.0296 |
| 47 | gpt-5.5-xhigh | gpt-5.5 | openai | xhigh | bare | 81.6% | 77.0% to 85.5% | 316 | $0.1913 |
| 48 | grok-4.7-high | grok-4.7 | x-ai | high | bare | 81.0% | 76.3% to 85.0% | 316 | $0.0803 |
| 49 | gpt-5.3-codex-high | gpt-5.3-codex | openai | high | bare | 81.0% | 76.3% to 85.0% | 316 | $0.0445 |
| 50 | gpt-6-sol-xhigh | gpt-6-sol | openai | xhigh | bare | 80.7% | 76.0% to 84.7% | 316 | $0.0111 |
| 51 | kimi-k3.1-pro-max | kimi-k3.1-pro | moonshotai | max | bare | 80.7% | 76.0% to 84.7% | 316 | $0.0935 |
| 52 | grok-4.6-high | grok-4.6 | x-ai | high | bare | 80.4% | 75.6% to 84.4% | 316 | $0.0365 |
| 53 | gpt-6.1-terra-low | gpt-6.1-terra | openai | low | bare | 80.4% | 75.6% to 84.4% | 316 | $0.0011 |
| 54 | gpt-5.5-high | gpt-5.5 | openai | high | bare | 80.4% | 75.6% to 84.4% | 316 | $0.1070 |
| 55 | claude-opus-4.5-16k | claude-opus-4.5 | anthropic | medium | bare | 80.1% | 75.3% to 84.1% | 316 | $0.1155 |
| 56 | gemini-3.1-pro-preview-high | gemini-3.1-pro-preview | high | bare | 79.7% | 75.0% to 83.8% | 316 | $0.0928 | |
| 57 | muse-wonder-high | muse-wonder | meta | high | bare | 79.4% | 74.6% to 83.5% | 316 | $0.1070 |
| 58 | claude-sonnet-4.6-high | claude-sonnet-4.6 | anthropic | high | bare | 79.4% | 74.6% to 83.5% | 316 | $0.1801 |
| 59 | gemini-3.7-flash-high | gemini-3.7-flash | high | bare | 79.1% | 74.3% to 83.2% | 316 | $0.0086 | |
| 60 | gpt-5.4-high | gpt-5.4 | openai | high | bare | 78.8% | 74.0% to 82.9% | 316 | $0.0484 |
| 61 | gpt-5.4-medium | gpt-5.4 | openai | medium | bare | 78.5% | 73.6% to 82.7% | 316 | $0.0185 |
| 62 | gpt-5.5-medium | gpt-5.5 | openai | medium | bare | 78.5% | 73.6% to 82.7% | 316 | $0.0427 |
| 63 | gpt-5.3-codex-medium | gpt-5.3-codex | openai | medium | bare | 77.8% | 73.0% to 82.1% | 316 | $0.0207 |
| 64 | grok-4.5-high | grok-4.5 | x-ai | high | bare | 76.3% | 71.3% to 80.6% | 316 | $0.0448 |
| 65 | gpt-5.6-sol-low | gpt-5.6-sol | openai | low | bare | 76.3% | 71.3% to 80.6% | 316 | $0.0121 |
| 66 | gpt-6-sol-low | gpt-6-sol | openai | low | bare | 75.6% | 70.6% to 80.0% | 316 | $0.0031 |
| 67 | kimi-k3-high | kimi-k3 | moonshotai | high | bare | 75.4% | 70.6% to 79.6% | 316 | $0.1165 |
| 68 | gpt-5.5-low | gpt-5.5 | openai | low | bare | 75.0% | 69.9% to 79.5% | 316 | $0.0246 |
| 69 | kimi-k3-max | kimi-k3 | moonshotai | max | bare | 74.4% | 69.3% to 78.9% | 316 | $0.1105 |
| 70 | gpt-5.6-terra-xhigh | gpt-5.6-terra | openai | xhigh | bare | 74.1% | 68.9% to 78.6% | 316 | $0.0303 |
| 71 | muse-spark-1.2-high | muse-spark-1.2 | meta | high | bare | 73.7% | 68.6% to 78.3% | 316 | $0.0394 |
| 72 | deepseek-v4.1-flash-1017-high | deepseek-v4.1-flash-1017 | deepseek | high | bare | 73.7% | 68.6% to 78.3% | 316 | $0.0027 |
| 73 | gpt-5.4-low | gpt-5.4 | openai | low | bare | 73.7% | 68.6% to 78.3% | 316 | $0.0124 |
| 74 | mimo-v2.6-pro-high | mimo-v2.6-pro | xiaomi | high | bare | 73.4% | 68.3% to 78.0% | 316 | $0.0241 |
| 75 | gemini-3.5-flash-high | gemini-3.5-flash | high | bare | 72.8% | 67.6% to 77.4% | 316 | $0.0849 | |
| 76 | muse-spark-open-high | muse-spark-open | meta | high | bare | 72.8% | 67.6% to 77.4% | 316 | $0.0484 |
| 77 | qwen3.7-max-high | qwen3.7-max | qwen | high | bare | 72.5% | 67.3% to 77.1% | 316 | $0.0232 |
| 78 | gemini-3-flash-high | gemini-3-flash | high | bare | 71.8% | 66.6% to 76.5% | 316 | $0.0256 | |
| 79 | gpt-6-luna-max | gpt-6-luna | openai | max | bare | 71.2% | 66.0% to 75.9% | 316 | $0.0018 |
| 80 | deepseek-v4.1-flash-high | deepseek-v4.1-flash | deepseek | high | bare | 70.6% | 65.3% to 75.3% | 316 | $0.0104 |
| 81 | qwen3.8-2.4t-a95b-high | qwen3.8-2.4t-a95b | qwen | high | bare | 70.3% | 65.0% to 75.0% | 316 | $0.0289 |
| 82 | claude-sonnet-4.5-high | claude-sonnet-4.5 | anthropic | high | bare | 70.3% | 65.0% to 75.0% | 316 | $0.0856 |
| 83 | gpt-5.4-mini-xhigh | gpt-5.4-mini | openai | xhigh | bare | 69.9% | 64.7% to 74.7% | 316 | $0.1200 |
| 84 | deepseek-v4-pro-0813-high | deepseek-v4-pro-0813 | deepseek | high | bare | 69.0% | 63.7% to 73.8% | 316 | $0.0791 |
| 85 | kimi-k2.6-high | kimi-k2.6 | moonshotai | high | bare | 69.0% | 63.7% to 73.8% | 316 | $0.0742 |
| 86 | claude-sonnet-5-low | claude-sonnet-5 | anthropic | low | bare | 68.4% | 63.0% to 73.2% | 316 | $0.0197 |
| 87 | gpt-5.6-terra-low | gpt-5.6-terra | openai | low | bare | 68.0% | 62.7% to 72.9% | 316 | $0.0108 |
| 88 | claude-opus-4.1-32k | claude-opus-4.1 | anthropic | high | bare | 67.1% | 61.7% to 72.0% | 316 | $0.2496 |
| 89 | kimi-k2.7-code-high | kimi-k2.7-code | moonshotai | high | bare | 65.5% | 60.1% to 70.5% | 316 | $0.0444 |
| 90 | kimi-k2.5-high | kimi-k2.5 | moonshotai | high | bare | 65.5% | 60.1% to 70.5% | 316 | $0.0140 |
| 91 | claude-opus-4.1-16k | claude-opus-4.1 | anthropic | medium | bare | 65.5% | 60.1% to 70.5% | 316 | $0.1979 |
| 92 | deepseek-v4-flash-0731 | deepseek-v4-flash-0731 | deepseek | max | bare | 64.9% | 59.8% to 69.8% | 316 | $0.0000 |
| 93 | gpt-5.4-mini-high | gpt-5.4-mini | openai | high | bare | 64.6% | 59.1% to 69.6% | 316 | $0.0336 |
| 94 | deepseek-v4-flash-0731-high | deepseek-v4-flash-0731 | deepseek | high | bare | 63.9% | 58.5% to 69.0% | 316 | $0.0000 |
| 95 | gpt-5.1-high | gpt-5.1 | openai | high | bare | 63.9% | 58.5% to 69.0% | 316 | $0.1240 |
| 96 | qwen3.8-flash-high | qwen3.8-flash | qwen | high | bare | 63.6% | 58.2% to 68.7% | 316 | $0.0188 |
| 97 | gpt-5.3-chat | gpt-5.3-chat | openai | - | bare | 63.0% | 57.5% to 68.1% | 316 | $0.0148 |
| 98 | claude-sonnet-4-5-16k | claude-sonnet-4.5 | anthropic | medium | bare | 63.0% | 57.5% to 68.1% | 316 | $0.0500 |
| 99 | kimi-k2.5 | kimi-k2.5 | moonshotai | - | bare | 62.7% | 57.2% to 67.8% | 316 | $0.0135 |
| 100 | gpt-5-high | gpt-5 | openai | high | bare | 62.3% | 56.9% to 67.5% | 316 | $0.0974 |
| 101 | deepseek-v4-pro-high | deepseek-v4-pro | deepseek | high | bare | 61.4% | 55.9% to 66.6% | 316 | $0.0285 |
| 102 | glm-5.2-high | glm-5.2 | z-ai | high | bare | 61.1% | 55.6% to 66.3% | 316 | $0.0406 |
| 103 | gpt-5.2-codex-low | gpt-5.2-codex | openai | low | bare | 60.8% | 55.3% to 66.0% | 316 | $0.0203 |
| 104 | gpt-5.4-mini-medium | gpt-5.4-mini | openai | medium | bare | 60.8% | 55.3% to 66.0% | 316 | $0.0163 |
| 105 | claude-sonnet-4-high | claude-sonnet-4 | anthropic | high | bare | 60.4% | 55.0% to 65.7% | 316 | $0.0712 |
| 106 | glm-5.3-flash-fp8-baseten-high-131k | glm-5.3-flash | z-ai | high | bare | 59.5% | 54.0% to 64.8% | 316 | $0.0051 |
| 107 | glm-5.3-flash-fp4-local-qad-high | glm-5.3-flash | z-ai | high | bare | 58.9% | 53.4% to 64.1% | 316 | $0.0000 |
| 108 | gpt-5.6-luna-low | gpt-5.6-luna | openai | low | bare | 57.9% | 52.4% to 63.2% | 316 | $0.0011 |
| 109 | claude-sonnet-4-16k | claude-sonnet-4 | anthropic | medium | bare | 57.9% | 52.4% to 63.2% | 316 | $0.0510 |
| 110 | qwen3.8-flash-xhigh | qwen3.8-flash | qwen | xhigh | bare | 57.6% | 52.1% to 62.9% | 316 | $0.0182 |
| 111 | hunter-alpha-high | hunter-alpha | openrouter | high | bare | 57.6% | 52.1% to 62.9% | 316 | $0.0000 |
| 112 | qwen3.6-plus-preview-high | qwen3.6-plus-preview | qwen | high | bare | 57.0% | 51.5% to 62.3% | 316 | $0.0000 |
| 113 | ox-alpha-high | ox-alpha | stealth | high | bare | 56.6% | 51.1% to 62.0% | 316 | $0.0000 |
| 114 | grok-4.20-beta-high | grok-4.20-beta | x-ai | high | bare | 56.3% | 50.8% to 61.7% | 316 | $0.0166 |
| 115 | grok-4.3-high | grok-4.3 | x-ai | high | bare | 56.3% | 50.8% to 61.7% | 316 | $0.0408 |
| 116 | mistral-large-4-0-high | mistral-large-4-0 | mistral | high | bare | 56.0% | 50.5% to 61.4% | 316 | $0.0228 |
| 117 | glm-5-high | glm-5 | z-ai | high | bare | 56.0% | 50.5% to 61.4% | 316 | $0.0279 |
| 118 | glm-5.3-high | glm-5.3 | z-ai | high | bare | 55.7% | 50.2% to 61.1% | 316 | $0.0367 |
| 119 | mimo-v2.5-pro-high | mimo-v2.5-pro | xiaomi | high | bare | 55.1% | 49.6% to 60.5% | 316 | $0.0066 |
| 120 | deepseek-v4-flash | deepseek-v4-flash | deepseek | max | bare | 54.7% | 49.2% to 60.1% | 316 | $0.0000 |
| 121 | glm-5.3-flash-nvfp4-sglang-h-high-65k | glm-5.3-flash | z-ai | high | bare | 54.4% | 48.9% to 59.8% | 316 | $0.0000 |
| 122 | minimax-m3-high | minimax-m3 | minimax | high | bare | 54.4% | 48.9% to 59.8% | 316 | $0.0165 |
| 123 | claude-3.7-sonnet-thinking | claude-3.7-sonnet | anthropic | high | bare | 54.1% | 48.6% to 59.5% | 316 | $0.1407 |
| 124 | deepseek-v4-flash-0731-low | deepseek-v4-flash-0731 | deepseek | low | bare | 53.5% | 48.0% to 58.9% | 316 | $0.0000 |
| 125 | qwen3.5-397b-a17b | qwen3.5-397b-a17b | qwen | - | bare | 52.8% | 47.3% to 58.3% | 316 | $0.0169 |
| 126 | glm-5.3-flash-nvfp4-qad-kraken-high-131k | glm-5.3-flash | z-ai | high | bare | 52.2% | 46.7% to 57.7% | 316 | $0.0000 |
| 127 | deepseek-v4-flash-high | deepseek-v4-flash | deepseek | high | bare | 51.6% | 46.1% to 57.0% | 316 | $0.0014 |
| 128 | gemini-3-flash | gemini-3-flash | - | bare | 51.6% | 46.1% to 57.0% | 316 | $0.0015 | |
| 129 | gpt-5.4-mini-low | gpt-5.4-mini | openai | low | bare | 51.3% | 45.8% to 56.7% | 316 | $0.0044 |
| 130 | deepseek-r1 | deepseek-r1 | deepseek | high | bare | 50.6% | 45.1% to 56.1% | 316 | $0.0139 |
| 131 | inkling-high | inkling | thinkingmachines | high | bare | 50.0% | 44.5% to 55.5% | 316 | $0.0578 |
| 132 | gemini-3.1-flash-lite-preview-high | gemini-3.1-flash-lite-preview | high | bare | 49.4% | 43.9% to 54.9% | 316 | $0.0092 | |
| 133 | qwen3-235b-a22b-thinking-2507 | qwen3-235b-a22b-thinking-2507 | qwen | high | bare | 49.1% | 43.6% to 54.5% | 316 | $0.0213 |
| 134 | gpt-5.3-codex-spark-xhigh | gpt-5.3-codex-spark | openai | xhigh | bare | 48.7% | 43.3% to 54.2% | 316 | $0.2953 |
| 135 | glm-4.7-high | glm-4.7 | z-ai | high | bare | 46.8% | 41.4% to 52.3% | 316 | $0.0186 |
| 136 | deepseek-r1-0528 | deepseek-r1-0528 | deepseek | high | bare | 46.2% | 40.8% to 51.7% | 316 | $0.0107 |
| 137 | minimax-m3.1-flash-xhigh | minimax-m3.1-flash | minimax | xhigh | bare | 46.2% | 40.8% to 51.7% | 316 | $0.0000 |
| 138 | qwen3-max-thinking | qwen3-max-thinking | qwen | high | bare | 45.9% | 40.5% to 51.4% | 316 | $0.0366 |
| 139 | healer-alpha-high | healer-alpha | openrouter | high | bare | 45.6% | 40.2% to 51.1% | 316 | $0.0000 |
| 140 | o4-mini-high | o4-mini | openai | high | bare | 44.6% | 39.2% to 50.1% | 316 | $0.0499 |
| 141 | grok-code-fast-1-high | grok-code-fast-1 | x-ai | high | bare | 44.0% | 38.6% to 49.5% | 316 | $0.0056 |
| 142 | claude-haiku-4.5-high | claude-haiku-4.5 | anthropic | high | bare | 43.7% | 38.3% to 49.2% | 316 | $0.0601 |
| 143 | qwen3.6-27b-high | qwen3.6-27b | qwen | high | bare | 43.7% | 38.3% to 49.2% | 316 | $0.0205 |
| 144 | qwen3.8-27b | qwen3.8-27b | qwen | xhigh | bare | 43.4% | 38.0% to 48.9% | 316 | $0.0000 |
| 145 | minimax-m2.7-high | minimax-m2.7 | minimax | high | bare | 43.0% | 37.7% to 48.5% | 316 | $0.0158 |
| 146 | qwen3.8-27b-nvfp4-xhigh | qwen3.8-27b | qwen | xhigh | bare | 42.7% | 37.4% to 48.2% | 316 | $0.0000 |
| 147 | qwen3.5-122b-a10b-sf | qwen3.5-122b-a10b | qwen | - | bare | 42.7% | 37.4% to 48.2% | 316 | $0.0000 |
| 148 | qwen3-max | qwen3-max | qwen | - | bare | 42.7% | 37.4% to 48.2% | 316 | $0.0028 |
| 149 | claude-haiku-4.5 | claude-haiku-4.5 | anthropic | - | bare | 42.1% | 36.8% to 47.6% | 316 | $0.0031 |
| 150 | minimax-m2.5 | minimax-m2.5 | minimax | - | bare | 40.6% | 35.6% to 45.8% | 316 | $0.0103 |
| 151 | gpt-oss-120b-low-ef-ecodev | gpt-oss-120b | openai | low | bare | 40.5% | 35.2% to 46.0% | 316 | $0.0000 |
| 152 | gpt-oss-120b-medium-ef-ecodev | gpt-oss-120b | openai | medium | bare | 39.6% | 34.3% to 45.0% | 316 | $0.0000 |
| 153 | qwen3.5-27b | qwen3.5-27b | qwen | - | bare | 39.6% | 34.3% to 45.0% | 316 | $0.0147 |
| 154 | deepseek-v3.1 | deepseek-v3.1 | deepseek | - | bare | 39.6% | 34.3% to 45.0% | 316 | $0.0010 |
| 155 | step-3.7-flash-high | step-3.7-flash | stepfun | high | bare | 38.9% | 33.7% to 44.4% | 316 | $0.0340 |
| 156 | gpt-oss-120b-medium | gpt-oss-120b | openai | medium | bare | 38.6% | 33.4% to 44.1% | 316 | $0.0004 |
| 157 | deepseek-v3.2 | deepseek-v3.2 | deepseek | - | bare | 38.3% | 33.1% to 43.8% | 316 | $0.0005 |
| 158 | llama-4-maverick | llama-4-maverick | meta | - | bare | 38.3% | 33.1% to 43.8% | 316 | $0.0005 |
| 159 | qwen3.8-27b-nvfp4-medium | qwen3.8-27b | qwen | medium | bare | 37.7% | 32.5% to 43.1% | 316 | $0.0000 |
| 160 | muse-glimmer-30b-high | muse-glimmer-30b | meta | high | bare | 37.7% | 32.5% to 43.1% | 316 | $0.0145 |
| 161 | deepseek-v3 | deepseek-v3 | deepseek | - | bare | 37.7% | 32.5% to 43.1% | 316 | $0.0005 |
| 162 | gemini-2.5-flash-high | gemini-2.5-flash | high | bare | 37.3% | 32.2% to 42.8% | 316 | $0.0146 | |
| 163 | gpt-oss-120b-high-ef-ecodev | gpt-oss-120b | openai | high | bare | 37.3% | 32.2% to 42.8% | 316 | $0.0000 |
| 164 | qwen3.6-35b-a3b-high | qwen3.6-35b-a3b | qwen | high | bare | 37.3% | 32.2% to 42.8% | 316 | $0.0081 |
| 165 | grok-4.1-fast-high | grok-4.1-fast | x-ai | high | bare | 36.7% | 31.6% to 42.2% | 316 | $0.0043 |
| 166 | owl-alpha | owl-alpha | openrouter | - | bare | 36.4% | 31.3% to 41.8% | 316 | $0.0000 |
| 167 | grok-3 | grok-3 | x-ai | - | bare | 36.4% | 31.3% to 41.8% | 316 | $0.0051 |
| 168 | mistral-small-2603-high | mistral-small-2603 | mistral | high | bare | 36.1% | 31.0% to 41.5% | 316 | $0.0028 |
| 169 | claude-3.5-haiku | claude-3.5-haiku | anthropic | - | bare | 35.8% | 30.7% to 41.2% | 316 | $0.0012 |
| 170 | qwen3.5-35b-a3b | qwen3.5-35b-a3b | qwen | - | bare | 35.8% | 30.7% to 41.2% | 316 | $0.0139 |
| 171 | grok-3-mini-high | grok-3-mini | x-ai | high | bare | 35.1% | 30.1% to 40.5% | 316 | $0.0041 |
| 172 | minimax-m2.5-high | minimax-m2.5 | minimax | high | bare | 34.5% | 29.5% to 39.9% | 316 | $0.0111 |
| 173 | mistral-large-2512 | mistral-large-2512 | mistral | - | bare | 34.2% | 29.2% to 39.6% | 316 | $0.0008 |
| 174 | qwen3.6-35b-a3b-q8 | qwen3.6-35b-a3b | qwen | - | bare | 33.9% | 28.9% to 39.2% | 316 | $0.0000 |
| 175 | qwen3.5-27b-uncensored | qwen3.5-27b-uncensored-hauhaucs-aggressive | qwen | - | bare | 33.9% | 28.9% to 39.2% | 316 | $0.0000 |
| 176 | mistral-medium-3.1 | mistral-medium-3.1 | mistral | - | bare | 33.2% | 28.3% to 38.6% | 316 | $0.0007 |
| 177 | grok-4-fast-high | grok-4-fast | x-ai | high | bare | 32.9% | 28.0% to 38.3% | 316 | $0.0036 |
| 178 | laguna-s-2.1-fp8 | laguna-s-2.1 | starflinger | - | bare | 32.6% | 27.7% to 37.9% | 316 | $0.0000 |
| 179 | gpt-oss-120b-low | gpt-oss-120b | openai | low | bare | 32.3% | 27.4% to 37.6% | 316 | $0.0001 |
| 180 | gpt-5-nano-high | gpt-5-nano | openai | high | bare | 32.0% | 27.1% to 37.3% | 316 | $0.0047 |
| 181 | gpt-4o-2024-05-13 | gpt-4o-2024-05-13 | openai | - | bare | 32.0% | 27.1% to 37.3% | 316 | $0.0061 |
| 182 | gpt-4o | gpt-4o | openai | - | bare | 31.6% | 26.8% to 37.0% | 316 | $0.0034 |
| 183 | flint-v1.0 | flint-v1.0 | recursive | - | bare | 31.3% | 26.5% to 36.6% | 316 | $0.0000 |
| 184 | gpt-4.1-mini | gpt-4.1-mini | openai | - | bare | 31.0% | 26.2% to 36.3% | 316 | $0.0016 |
| 185 | codestral-2508 | codestral-2508 | mistral | - | bare | 31.0% | 26.2% to 36.3% | 316 | $0.0004 |
| 186 | mixtral-8x22b-instruct | mixtral-8x22b-instruct | mistral | - | bare | 30.7% | 25.9% to 36.0% | 316 | $0.0019 |
| 187 | laguna-s-2.1-nvfp4-thinking | laguna-s-2.1 | starflinger | high | bare | 30.7% | 25.9% to 36.0% | 316 | $0.0000 |
| 188 | laguna-s-2.1-fp8-thinking | laguna-s-2.1 | starflinger | high | bare | 29.4% | 24.7% to 34.7% | 316 | $0.0000 |
| 189 | gemma-4-31b-it-high | gemma-4-31b-it | high | bare | 29.1% | 24.4% to 34.3% | 316 | $0.0019 | |
| 190 | gpt-oss-20b-high | gpt-oss-20b | openai | high | bare | 28.8% | 24.1% to 34.0% | 316 | $0.0029 |
| 191 | devstral-medium | devstral-medium | mistral | - | bare | 28.8% | 24.1% to 34.0% | 316 | $0.0010 |
| 192 | gpt-oss-20b-medium | gpt-oss-20b | openai | medium | bare | 28.5% | 23.8% to 33.7% | 316 | $0.0006 |
| 193 | laguna-s-2.1-nvfp4 | laguna-s-2.1 | starflinger | - | bare | 28.2% | 23.5% to 33.4% | 316 | $0.0000 |
| 194 | qwq-32b | qwq-32b | qwen | high | bare | 27.5% | 22.9% to 32.7% | 316 | $0.0044 |
| 195 | mistral-large-2411 | mistral-large-2411 | mistral | - | bare | 27.2% | 22.6% to 32.4% | 316 | $0.0046 |
| 196 | gemini-2.0-flash | gemini-2.0-flash | - | bare | 26.9% | 22.3% to 32.0% | 316 | $0.0002 | |
| 197 | qwen-2.5-72b-instruct | qwen-2.5-72b-instruct | qwen | - | bare | 26.3% | 21.7% to 31.4% | 316 | $0.0004 |
| 198 | gpt-4-turbo | gpt-4-turbo | openai | - | bare | 26.3% | 21.7% to 31.4% | 316 | $0.0150 |
| 199 | llama-4-scout | llama-4-scout | meta | - | bare | 25.3% | 20.8% to 30.4% | 316 | $0.0002 |
| 200 | hermes-4-405b | hermes-4-405b | nousresearch | - | bare | 24.4% | 20.0% to 29.4% | 316 | $0.0009 |
| 201 | gemma-4-26b-a4b-it-high | gemma-4-26b-a4b-it | high | bare | 24.4% | 20.0% to 29.4% | 316 | $0.0036 | |
| 202 | command-a | command-a | cohere | - | bare | 23.7% | 19.4% to 28.7% | 316 | $0.0043 |
| 203 | claude-3-haiku | claude-3-haiku | anthropic | - | bare | 23.7% | 20.6% to 27.2% | 316 | $0.0004 |
| 204 | glm-4.7-flash-high | glm-4.7-flash | z-ai | high | bare | 23.7% | 19.4% to 28.7% | 316 | $0.0032 |
| 205 | llama-3.3-70b-instruct | llama-3.3-70b-instruct | meta | - | bare | 23.1% | 18.8% to 28.1% | 316 | $0.0003 |
| 206 | gemini-2.5-flash-lite | gemini-2.5-flash-lite | - | bare | 21.2% | 17.1% to 26.0% | 316 | $0.0004 | |
| 207 | gpt-4.1-nano | gpt-4.1-nano | openai | - | bare | 20.3% | 16.2% to 25.0% | 316 | $0.0002 |
| 208 | llama-3.1-instruct-70b | llama-3.1-instruct-70b | meta | - | bare | 19.9% | 15.9% to 24.7% | 316 | $0.0003 |
| 209 | gpt-4o-mini | gpt-4o-mini | openai | - | bare | 18.4% | 14.5% to 23.0% | 316 | $0.0002 |
| 210 | command-r-plus | command-r-plus | cohere | - | bare | 18.0% | 14.2% to 22.7% | 316 | $0.0021 |
| 211 | gpt-3.5-turbo | gpt-3.5-turbo | openai | - | bare | 17.4% | 13.6% to 22.0% | 316 | $0.0003 |
| 212 | command-r | command-r | cohere | - | bare | 17.1% | 13.3% to 21.6% | 316 | $0.0001 |
| 213 | hermes-4-70b | hermes-4-70b | nousresearch | - | bare | 16.5% | 12.8% to 20.9% | 316 | $0.0001 |
| 214 | phi-4 | phi-4 | microsoft | - | bare | 15.5% | 11.9% to 19.9% | 316 | $0.0001 |
| 215 | llama-3-instruct-8b | llama-3-instruct-8b | meta | - | bare | 10.8% | 7.8% to 14.7% | 316 | $0.0000 |
| 216 | llama-3.1-instruct-8b | llama-3.1-instruct-8b | meta | - | bare | 9.5% | 6.7% to 13.2% | 316 | $0.0000 |
| 217 | llama-3.2-instruct-3b | llama-3.2-instruct-3b | meta | - | bare | 7.0% | 4.6% to 10.3% | 316 | $0.0001 |
| 218 | mixtral-8x7b-instruct | mixtral-8x7b-instruct | mistral | - | bare | 6.0% | 3.9% to 9.2% | 316 | $0.0005 |
| 219 | llama-3.2-instruct-1b | llama-3.2-instruct-1b | meta | - | bare | 0.6% | 0.2% to 2.3% | 316 | $0.0003 |