| 46 | Z.AI GLM 5 Turbo | $0.0063 | 16.7s | 99% | 100 | 100 | 100 | 100 | 100 | 99 | 99 | 100% |
| 71 | GPT-5.5 | $0.017 | 4.7s | 99% | 100 | 100 | 100 | 100 | 99 | 99 | 99 | 100% |
| 74 | Claude Opus 4.6 (Reasoning) | $0.017 | 6.1s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 139 | Qwen3.6 Max Preview | $0.033 | 1.8m | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 88 | Claude Opus 4.7 (Reasoning) | $0.022 | 4.0s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 96 | Claude Opus 4.8 (Reasoning) | $0.023 | 7.7s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 69 | Claude Opus 4.6 | $0.016 | 5.6s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 21 | GPT-5.4 Mini (Reasoning) | $0.0050 | 6.2s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 110 | Gemma 4 31B (Reasoning) | $0.0008 | 1.8m | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 49 | Claude Sonnet 4 | $0.0099 | 5.9s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 24 | Gemma 4 31B | $0.0003 | 26.8s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 42 | GPT-5.6 Terra | $0.0087 | 2.5s | 99% | 100 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 43 | GPT-5.6 Terra (Reasoning) | $0.0087 | 3.0s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 65 | Grok 4.20 (Reasoning) | $0.0078 | 29.5s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 117 | Grok 4.5 (Reasoning, High) | $0.023 | 37.2s | 99% | 100 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 73 | Aion 2.0 | $0.0041 | 56.1s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 105 | DeepSeek V4 Pro (Reasoning) | $0.0046 | 1.4m | 98% | 100 | 100 | 99 | 99 | 99 | 99 | 98 | 99% |
| 12 | Claude Haiku 4.5 | $0.0033 | 2.8s | 99% | 100 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 56 | GPT-5.1 | $0.0087 | 10.8s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 86 | GPT-5.6 Sol (Reasoning) | $0.021 | 7.9s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 125 | Claude Sonnet 4.6 (Reasoning) | $0.033 | 25.1s | 98% | 100 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 127 | Gemini 2.5 Pro | $0.035 | 26.1s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 47 | GPT-5.4 | $0.0087 | 5.5s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 94 | Claude Opus 4.7 | $0.022 | 4.2s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 17 | Z.AI GLM 5.2 (Reasoning, High) | $0.0029 | 8.9s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 115 | Gemini 3.5 Flash (Reasoning) | $0.028 | 12.0s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 52 | Claude Sonnet 4.5 | $0.0099 | 4.5s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 19 | DeepSeek V4 Pro | $0.0013 | 16.3s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 79 | GPT-5.5 (Reasoning, Low) | $0.018 | 5.4s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 97 | 99% |
| 135 | Claude Opus 4 | $0.050 | 7.7s | 96% | 100 | 100 | 100 | 99 | 99 | 99 | 95 | 99% |
| 48 | DeepSeek V3.1 | $0.0007 | 36.6s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 62 | GPT-5.4 (Reasoning) | $0.011 | 8.5s | 97% | 100 | 99 | 99 | 99 | 99 | 99 | 96 | 99% |
| 131 | Qwen3.7 Max | $0.034 | 1.0m | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 98 | Claude Opus 4.8 (Reasoning, Low) | $0.022 | 7.2s | 97% | 99 | 99 | 99 | 99 | 99 | 99 | 96 | 99% |
| 91 | Gemma 4 26B (Reasoning) | $0.0008 | 1.4m | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 37 | Xiaomi MIMO v2.5 Pro | $0.0034 | 15.4s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 59 | Qwen 3.5 Flash | $0.0026 | 40.4s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 9 | Gemma 4 26B | $0.0002 | 11.9s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 16 | GPT-4.1 Mini | $0.0010 | 12.0s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 35 | Hermes 3 405B | $0.0011 | 23.7s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 112 | Qwen 3.5 27B | $0.013 | 57.8s | 97% | 99 | 99 | 99 | 99 | 99 | 99 | 96 | 99% |
| 138 | Gemini 3.1 Pro (Preview) | $0.047 | 44.2s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 77 | Z.AI GLM 5.1 | $0.0096 | 35.3s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 124 | Qwen 3.5 397B A17B | $0.0073 | 2.1m | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 53 | Claude Sonnet 4.6 | $0.0099 | 4.8s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 54 | Claude Sonnet 5 (Reasoning) | $0.0092 | 8.0s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 72 | Claude Opus 4.5 | $0.016 | 5.1s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 64 | Qwen 3.6 Flash | $0.0077 | 25.1s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 50 | Claude Sonnet 5 | $0.0090 | 7.7s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 44 | MiniMax M2.7 | $0.0026 | 23.8s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 7 | Qwen 3.5 Plus (2026-02-15) | $0.0014 | 6.7s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 101 | DeepSeek V3.2 | $0.0003 | 1.7m | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 33 | GPT-4o, Aug. 6th (temp=0) | $0.0063 | 2.9s | 99% | 99 | 99 | 99 | 99 | 99 | 99 | 99 | 99% |
| 60 | Gemini 3 Flash (Preview, Reasoning) | $0.0089 | 14.6s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 57 | Claude Sonnet 5 (Reasoning, Low) | $0.0093 | 7.9s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 2 | Gemini 3.1 Flash Lite (Reasoning) | $0.0009 | 1.8s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 3 | GPT-5.4 Nano | $0.0007 | 3.2s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 13 | Hermes 3 70B | $0.0003 | 13.7s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 40 | DeepSeek V4 Flash (Reasoning) | $0.0005 | 23.9s | 97% | 100 | 99 | 99 | 99 | 99 | 99 | 96 | 99% |
| 82 | Z.AI GLM 5 | $0.0055 | 57.1s | 98% | 99 | 99 | 99 | 99 | 99 | 99 | 98 | 99% |
| 18 | Xiaomi MIMO v2.5 | $0.0021 | 9.1s | 97% | 100 | 99 | 99 | 99 | 99 | 98 | 97 | 99% |
| 142 | MoonshotAI: Kimi K2.5 | $0.012 | 3.3m | 97% | 99 | 99 | 99 | 99 | 99 | 99 | 97 | 99% |
| 28 | GPT-4.1 | $0.0050 | 4.4s | 98% | 99 | 99 | 99 | 99 | 98 | 98 | 98 | 99% |
| 1 | Gemini 2.5 Flash Lite | $0.0003 | 1.8s | 98% | 99 | 99 | 99 | 99 | 98 | 98 | 98 | 99% |
| 130 | Z.AI GLM 4.7 | $0.0089 | 2.4m | 97% | 99 | 99 | 99 | 99 | 99 | 97 | 96 | 99% |
| 104 | Grok 4.3 (Reasoning) | $0.011 | 53.3s | 96% | 100 | 100 | 99 | 99 | 98 | 97 | 96 | 99% |
| 111 | MiniMax M3 | $0.0041 | 1.5m | 96% | 99 | 99 | 99 | 99 | 99 | 98 | 95 | 99% |
| 4 | Gemini 3.1 Flash Lite | $0.0009 | 1.8s | 98% | 99 | 99 | 99 | 99 | 98 | 98 | 98 | 98% |
| 10 | Qwen 2.5 72B | $0.0003 | 9.5s | 98% | 99 | 99 | 99 | 98 | 98 | 98 | 98 | 98% |
| 103 | Qwen 3.5 35B | $0.014 | 40.4s | 96% | 99 | 99 | 99 | 99 | 99 | 98 | 95 | 98% |
| 11 | Gemini 3 Flash (Preview) | $0.0018 | 3.1s | 97% | 99 | 99 | 99 | 98 | 98 | 98 | 98 | 98% |
| 141 | MoonshotAI: Kimi K2.6 | $0.019 | 2.6m | 97% | 99 | 99 | 99 | 99 | 99 | 99 | 95 | 98% |
| 75 | ByteDance Seed 2.0 Lite | $0.0044 | 48.5s | 97% | 99 | 99 | 99 | 99 | 99 | 99 | 95 | 98% |
| 20 | GPT-5.4 Mini (Reasoning, Low) | $0.0027 | 3.9s | 96% | 99 | 99 | 99 | 99 | 99 | 98 | 95 | 98% |
| 34 | Gemini 3.5 Flash (Reasoning, Minimal) | $0.0053 | 2.5s | 97% | 99 | 99 | 98 | 98 | 98 | 98 | 98 | 98% |
| 76 | GPT-5 Mini | $0.0066 | 41.1s | 97% | 99 | 99 | 99 | 99 | 98 | 98 | 96 | 98% |
| 45 | Gemini 2.5 Flash (Reasoning) | $0.0058 | 8.8s | 97% | 99 | 99 | 98 | 98 | 98 | 98 | 98 | 98% |
| 5 | Gemini 3.1 Flash Lite (Preview) | $0.0009 | 1.7s | 98% | 98 | 98 | 98 | 98 | 98 | 98 | 98 | 98% |
| 41 | GPT-4o, Aug. 6th (temp=1) | $0.0063 | 2.6s | 97% | 99 | 99 | 98 | 98 | 98 | 97 | 97 | 98% |
| 15 | Cydonia 24B V4.1 | $0.0004 | 11.5s | 98% | 99 | 98 | 98 | 98 | 98 | 98 | 98 | 98% |
| 116 | GPT-5.5 (Reasoning) | $0.027 | 10.5s | 96% | 100 | 99 | 99 | 99 | 97 | 96 | 96 | 98% |
| 84 | GPT-5.6 Sol | $0.017 | 3.8s | 96% | 99 | 99 | 99 | 99 | 99 | 95 | 95 | 98% |
| 122 | Qwen 3.5 Plus (2026-04-20) | $0.014 | 1.4m | 96% | 99 | 99 | 99 | 99 | 97 | 97 | 95 | 98% |
| 129 | GPT-5 | $0.027 | 42.1s | 93% | 99 | 99 | 99 | 99 | 99 | 99 | 90 | 98% |
| 23 | Gemma 3 27B | $0.0002 | 13.1s | 95% | 99 | 99 | 99 | 98 | 98 | 98 | 94 | 98% |
| 120 | Qwen 3.5 122B | $0.020 | 48.7s | 96% | 99 | 99 | 99 | 99 | 96 | 96 | 95 | 98% |
| 6 | Mistral Small 3.2 24B | $0.0002 | 4.4s | 97% | 98 | 98 | 98 | 98 | 98 | 98 | 98 | 98% |
| 8 | GPT-4.1 Nano | $0.0003 | 3.6s | 96% | 99 | 98 | 98 | 98 | 98 | 97 | 96 | 98% |
| 108 | Grok 4.5 (Reasoning, Low) | $0.0095 | 52.2s | 93% | 99 | 99 | 99 | 99 | 99 | 97 | 90 | 98% |
| 89 | ByteDance Seed 1.6 | $0.0051 | 57.2s | 95% | 100 | 99 | 99 | 99 | 97 | 96 | 93 | 98% |
| 14 | Mistral Large 3 | $0.0010 | 7.1s | 98% | 98 | 98 | 98 | 98 | 98 | 98 | 98 | 98% |
| 36 | Mistral Large 2 | $0.0041 | 7.3s | 98% | 98 | 98 | 98 | 98 | 98 | 98 | 98 | 98% |
| 67 | Qwen 3.6 35B | $0.0052 | 33.0s | 95% | 99 | 99 | 99 | 99 | 95 | 95 | 95 | 98% |
| 22 | DeepSeek V4 Flash | $0.0002 | 8.1s | 94% | 99 | 99 | 99 | 99 | 99 | 98 | 91 | 98% |
| 90 | o4 Mini High | $0.014 | 24.4s | 95% | 99 | 99 | 98 | 98 | 97 | 96 | 95 | 98% |
| 25 | DeepSeek V3 (2024-12-26) | $0.0007 | 14.3s | 97% | 98 | 98 | 98 | 98 | 98 | 97 | 96 | 97% |
| 30 | DeepSeek-V2 Chat | $0.0008 | 15.2s | 97% | 98 | 98 | 98 | 97 | 97 | 97 | 97 | 97% |
| 58 | DeepSeek V3 (2025-03-24) | $0.0006 | 38.8s | 96% | 98 | 98 | 97 | 97 | 97 | 97 | 96 | 97% |
| 97 | GPT-OSS 120B | $0.0005 | 1.3m | 93% | 99 | 99 | 99 | 96 | 96 | 96 | 95 | 97% |
| 92 | MiniMax M2.5 | $0.0021 | 1.1m | 93% | 99 | 99 | 96 | 96 | 96 | 95 | 95 | 97% |
| 87 | o4 Mini | $0.013 | 22.6s | 94% | 98 | 98 | 98 | 98 | 97 | 96 | 93 | 97% |
| 26 | GPT-5.4 Nano (Reasoning, Low) | $0.0007 | 2.8s | 92% | 99 | 99 | 99 | 95 | 95 | 95 | 95 | 97% |
| 55 | GPT-5.6 Luna (Reasoning) | $0.0043 | 4.2s | 91% | 99 | 99 | 99 | 97 | 96 | 96 | 90 | 97% |
| 31 | GPT-5.6 Luna | $0.0035 | 3.2s | 97% | 97 | 97 | 97 | 97 | 97 | 97 | 97 | 97% |
| 27 | GPT-5.4 Nano (Reasoning) | $0.0007 | 3.1s | 93% | 99 | 99 | 99 | 98 | 95 | 95 | 90 | 97% |
| 95 | Z.AI GLM 4.7 Flash | $0.0012 | 1.1m | 93% | 99 | 99 | 98 | 96 | 95 | 95 | 94 | 97% |
| 38 | GPT-5.4 Mini | $0.0026 | 2.1s | 93% | 100 | 96 | 96 | 96 | 96 | 96 | 95 | 97% |
| 66 | Z.AI GLM 4.5 Air | $0.0016 | 32.3s | 92% | 99 | 99 | 95 | 95 | 95 | 95 | 95 | 97% |
| 118 | Z.AI GLM 4.6 | $0.0086 | 1.2m | 92% | 99 | 99 | 96 | 96 | 96 | 95 | 93 | 96% |
| 63 | WizardLM 2 8x22b | $0.0007 | 35.2s | 93% | 99 | 98 | 97 | 96 | 96 | 95 | 93 | 96% |
| 29 | Mistral Medium 3.1 | $0.0012 | 5.8s | 95% | 97 | 97 | 96 | 96 | 96 | 96 | 96 | 96% |
| 39 | GPT-4o Mini (temp=1) | $0.0004 | 9.6s | 93% | 99 | 95 | 95 | 95 | 95 | 95 | 95 | 96% |
| 32 | GPT-4o Mini (temp=0) | $0.0004 | 9.6s | 95% | 95 | 95 | 95 | 95 | 95 | 95 | 95 | 95% |
| 78 | GPT-5.4 (Reasoning, Low) | $0.0089 | 5.0s | 88% | 99 | 99 | 99 | 95 | 93 | 90 | 90 | 95% |
| 70 | GPT-5.2 | $0.0078 | 5.2s | 89% | 99 | 99 | 99 | 96 | 93 | 90 | 90 | 95% |
| 114 | Aion 3.0 | $0.0092 | 25.2s | 79% | 99 | 99 | 99 | 99 | 99 | 98 | 70 | 95% |
| 83 | Gemini 2.5 Flash Lite (Reasoning) | $0.0033 | 31.4s | 87% | 100 | 99 | 99 | 99 | 90 | 90 | 84 | 95% |
| 68 | Gemma 3 12B | $0.0001 | 9.3s | 79% | 99 | 99 | 98 | 98 | 98 | 98 | 70 | 94% |
| 51 | Inception Mercury 2 | $0.0013 | 1.6s | 88% | 97 | 96 | 96 | 95 | 95 | 95 | 84 | 94% |
| 80 | Gemini 2.5 Flash | $0.0015 | 2.1s | 72% | 99 | 99 | 99 | 99 | 99 | 98 | 60 | 94% |
| 85 | Z.AI GLM 4.5 | $0.0039 | 32.3s | 88% | 96 | 96 | 96 | 93 | 90 | 90 | 90 | 93% |
| 99 | GPT-5 Nano | $0.0018 | 43.9s | 85% | 96 | 95 | 93 | 90 | 90 | 90 | 89 | 92% |
| 133 | Qwen 3.5 9B | $0.0012 | 1.9m | 72% | 99 | 99 | 99 | 96 | 95 | 93 | 61 | 92% |
| 81 | Grok 4.3 | $0.0019 | 4.7s | 77% | 99 | 99 | 97 | 96 | 93 | 84 | 70 | 91% |
| 61 | Grok 4.20 | $0.0018 | 4.4s | 89% | 92 | 92 | 92 | 91 | 91 | 91 | 88 | 91% |
| 100 | Qwen 3 32B | $0.0009 | 31.4s | 79% | 98 | 98 | 95 | 94 | 90 | 84 | 75 | 91% |
| 93 | Llama 3.1 70B | $0.0004 | 14.4s | 78% | 98 | 90 | 88 | 87 | 83 | 83 | 83 | 87% |
| 126 | Mistral Small 4 (Reasoning) | $0.0016 | 13.5s | 48% | 99 | 98 | 98 | 98 | 96 | 96 | 25 | 87% |
| 132 | ByteDance Seed 2.0 Mini | $0.0017 | 1.7m | 73% | 98 | 93 | 90 | 89 | 85 | 83 | 68 | 86% |
| 102 | Qwen3 235B A22B Instruct 2507 | $0.0004 | 16.7s | 77% | 94 | 89 | 86 | 84 | 84 | 82 | 81 | 86% |
| 140 | Qwen 3.6 27B | $0.013 | 56.0s | 55% | 99 | 99 | 97 | 96 | 96 | 76 | 36 | 86% |
| 121 | Mistral Small 4 | $0.0004 | 4.8s | 55% | 98 | 98 | 98 | 98 | 96 | 67 | 38 | 85% |
| 107 | Ministral 3 3B | $0.0001 | 2.2s | 70% | 96 | 91 | 87 | 81 | 81 | 78 | 76 | 84% |
| 106 | Writer: Palmyra X5 | $0.0032 | 7.5s | 80% | 86 | 84 | 84 | 82 | 82 | 82 | 81 | 83% |
| 128 | ByteDance Seed 1.6 Flash | $0.0009 | 16.7s | 52% | 98 | 94 | 94 | 91 | 90 | 82 | 32 | 83% |
| 119 | Ministral 3B | $0.0000 | 2.8s | 62% | 96 | 96 | 90 | 81 | 76 | 69 | 65 | 82% |
| 136 | Nemotron 3 Super | $0.0000 | 46.4s | 46% | 99 | 97 | 96 | 93 | 93 | 70 | 23 | 82% |
| 109 | Mistral NeMO | $0.0002 | 2.3s | 73% | 88 | 86 | 80 | 79 | 79 | 78 | 77 | 81% |
| 145 | Aion 3.0 Mini | $0.0044 | 1.5m | 30% | 100 | 99 | 99 | 99 | 99 | 61 | 0 | 80% |
| 113 | Ministral 3 14B | $0.0002 | 3.8s | 75% | 78 | 78 | 78 | 78 | 78 | 76 | 73 | 77% |
| 144 | Nemotron 3 Nano | $0.0006 | 36.4s | 30% | 96 | 93 | 93 | 92 | 85 | 22 | 14 | 71% |
| 123 | Gemma 3 4B | $0.0001 | 5.1s | 68% | 70 | 70 | 70 | 70 | 67 | 67 | 67 | 69% |
| 143 | Arcee AI: Trinity Mini | $0.0002 | 8.0s | 21% | 94 | 93 | 93 | 92 | 89 | 7 | 6 | 68% |
| 134 | Ministral 8B | $0.0001 | 4.3s | 55% | 68 | 66 | 63 | 62 | 57 | 54 | 53 | 60% |
| 137 | Ministral 3 8B | $0.0002 | 2.9s | 53% | 64 | 64 | 62 | 61 | 57 | 54 | 44 | 58% |
| 146 | Cohere Command R+ (Aug. 2024) | $0.0062 | 13.8s | 9% | 96 | 27 | 25 | 22 | 18 | 11 | 3 | 29% |