| Model | Date | PTS | PTS% | W | GRP | TRAP | INV | AVG/G | TOK/G | COST | $/G |
|---|---|---|---|---|---|---|---|---|---|---|---|
| openai/gpt-6-astra | 2026-09-04 | 94 | 94.0% | 20 | 80/80 | 34 | 0 | 15s | 1.1k | $0.67 | $0.034 |
| x-ai/grok-4.6 | 2026-08-12 | 91 | 91.0% | 19 | 78/80 | 32 | 0 | 27s | 3.1k | $0.31 | $0.015 |
| meta/muse-spark-1.1 | 2026-07-22 | 90 | 90.0% | 20 | 80/80 | 30 | 0 | 38s | 5.4k | $0.42 | $0.021 |
| google/gemini-3.8-flash | 2026-09-02 | 88 | 88.0% | 20 | 80/80 | 28 | 0 | 8s | 2.5k | $0.15 | $0.008 |
| google/gemini-3.1-pro-preview | 2026-07-22 | 86 | 86.0% | 20 | 80/80 | 26 | 0 | 14s | 2.2k | $0.42 | $0.021 |
| openai/gpt-5.6-terra | 2026-07-22 | 86 | 86.0% | 20 | 80/80 | 26 | 0 | 19s | 2.0k | $0.47 | $0.024 |
| anthropic/claude-fable-5 | 2026-07-22 | 85 | 85.0% | 19 | 78/80 | 26 | 0 | 33s | 1.7k | $1.08 | $0.054 |
| google/gemini-3-flash-preview | 2026-07-22 | 84 | 84.0% | 20 | 80/80 | 24 | 0 | 10s | 2.6k | $0.13 | $0.006 |
| meta/muse-spark-1.3 | 2026-09-02 | 84 | 84.0% | 19 | 77/80 | 26 | 0 | 15s | 2.6k | $0.19 | $0.009 |
| openai/gpt-5.6-sol-pro | 2026-07-22 | 84 | 84.0% | 20 | 80/80 | 24 | 0 | 47s | 10.0k | $2.68 | $0.134 |
| moonshotai/kimi-k3 | 2026-07-22 | 84 | 84.0% | 18 | 74/80 | 28 | 0 | 51s | 2.3k | $0.55 | $0.027 |
| sakana/fugu-ultra | 2026-07-22 | 84 | 84.0% | 20 | 80/80 | 24 | 0 | 2m58s | 24.1k | $9.54 | $0.477 |
| openai/gpt-5.6-sol | 2026-07-22 | 83 | 83.0% | 17 | 72/80 | 28 | 1 | 27s | 1.5k | $0.63 | $0.032 |
| anthropic/claude-fable-5.1 | 2026-09-01 | 82 | 82.0% | 19 | 77/80 | 24 | 0 | 18s | 1.9k | $1.32 | $0.066 |
| x-ai/grok-4.20 | 2026-07-22 | 82 | 82.0% | 20 | 80/80 | 22 | 0 | 1m20s | 7.9k | $0.37 | $0.019 |
| google/gemini-3.7-flash | 2026-08-13 | 80 | 80.0% | 20 | 80/80 | 20 | 0 | 4s | 1.7k | $0.10 | $0.005 |
| meta/muse-spark-1.3-contributor | 2026-09-02 | 80 | 80.0% | 17 | 73/80 | 24 | 0 | 51s | 2.8k | $0.01 | $0.001 |
| deepseek/deepseek-v4-pro-0813 | 2026-08-12 | 80 | 80.0% | 20 | 80/80 | 20 | 0 | 9m20s | 16.1k | $0.28 | $0.014 |
| z-ai/glm-5.3-flash | 2026-08-28 | 78 | 78.0% | 20 | 80/80 | 18 | 0 | 1m52s | 4.1k | $0.02 | $0.001 |
| meta/muse-spark-1.2 | 2026-08-07 | 77 | 77.0% | 18 | 75/80 | 20 | 0 | 16s | 3.0k | $0.22 | $0.011 |
| openai/gpt-5.6-terra-pro | 2026-07-22 | 77 | 77.0% | 19 | 78/80 | 18 | 0 | 36s | 13.4k | $1.98 | $0.099 |
| deepseek/deepseek-v4-flash-0731 | 2026-07-31 | 77 | 77.0% | 19 | 76/80 | 20 | 1 | 2m50s | 20.4k | $0.11 | $0.006 |
| x-ai/grok-4.5 | 2026-07-22 | 76 | 76.0% | 18 | 74/80 | 20 | 1 | 1m3s | 4.4k | $0.44 | $0.022 |
| qwen/qwen3.8-flash | 2026-09-01 | 75 | 75.0% | 19 | 76/80 | 18 | 1 | 13m35s | 59.6k | $0.56 | $0.028 |
| anthropic/claude-opus-5 | 2026-07-24 | 74 | 74.0% | 20 | 80/80 | 14 | 0 | 8s | 1.4k | $0.40 | $0.020 |
| openai/gpt-5.6-luna | 2026-07-30 | 74 | 74.0% | 14 | 64/80 | 24 | 1 | 16s | 2.1k | $0.02 | $0.001 |
| meta/muse-spark-1.2-contributor | 2026-08-28 | 74 | 74.0% | 19 | 77/80 | 16 | 0 | 30s | 3.0k | $0.01 | $0.001 |
| z-ai/glm-5v-turbo | 2026-07-22 | 74 | 74.0% | 16 | 70/80 | 20 | 0 | 1m6s | 5.8k | $0.44 | $0.022 |
| bytedance-seed/seed-2-1-turbo | 2026-08-12 | 73 | 73.0% | 19 | 76/80 | 16 | 0 | 7m0s | 26.0k | $1.28 | $0.064 |
| openai/gpt-5.6-luna-pro | 2026-07-30 | 72 | 72.0% | 17 | 73/80 | 16 | 0 | 28s | 12.4k | $0.07 | $0.004 |
| anthropic/claude-sonnet-5 | 2026-07-22 | 71 | 71.0% | 16 | 71/80 | 16 | 0 | 15s | 2.1k | $0.30 | $0.015 |
| anthropic/claude-opus-4.5 | 2026-07-22 | 70 | 70.0% | 18 | 74/80 | 14 | 0 | 56s | 4.1k | $1.82 | $0.091 |
| google/gemini-3.6-flash | 2026-07-22 | 69 | 69.0% | 19 | 76/80 | 12 | 0 | 11s | 2.8k | $0.36 | $0.018 |
| deepseek/deepseek-v4-flash | 2026-07-22 | 68 | 71.6% | 14 | 64/80 | 18 | 1 | 7m12s | 15.0k | $0.08 | $0.004 |
| google/gemini-3.5-flash-lite | 2026-07-22 | 67 | 67.0% | 16 | 69/80 | 14 | 0 | 8s | 2.8k | $0.12 | $0.006 |
| google/gemini-3.5-flash | 2026-07-22 | 67 | 67.0% | 17 | 68/80 | 16 | 3 | 10s | 2.7k | $0.42 | $0.021 |
| thinkingmachines/inkling | 2026-07-22 | 67 | 67.0% | 16 | 67/80 | 16 | 1 | 2m42s | 3.2k | $0.22 | $0.011 |
| qwen/qwen3.8-max | 2026-08-12 | 67 | 67.0% | 16 | 67/80 | 16 | 2 | 2m56s | 10.9k | $1.27 | $0.064 |
| qwen/qwen3.8-2.4t-a95b | 2026-08-12 | 66 | 66.0% | 14 | 62/80 | 18 | 3 | 12m1s | 16.8k | $1.61 | $0.080 |
| anthropic/claude-opus-4.7 | 2026-07-22 | 65 | 65.0% | 19 | 76/80 | 8 | 1 | 14s | 1.7k | $0.49 | $0.024 |
| stepfun/step-3.7-flash | 2026-07-22 | 63 | 63.0% | 12 | 61/80 | 14 | 1 | 1m23s | 14.3k | $0.32 | $0.016 |
| meta/muse-glimmer-30b | 2026-08-12 | 61 | 61.0% | 10 | 53/80 | 18 | 1 | 27s | 4.1k | $0.09 | $0.005 |
| anthropic/claude-haiku-4.5 | 2026-07-22 | 60 | 60.0% | 13 | 59/80 | 14 | 1 | 30s | 4.3k | $0.39 | $0.019 |
| z-ai/glm-5.3 | 2026-08-28 | 57 | 57.0% | 17 | 68/80 | 6 | 3 | 5m30s | 16.4k | $1.41 | $0.070 |
| bytedance-seed/seed-2.0-code | 2026-08-12 | 56 | 56.0% | 13 | 57/80 | 12 | 0 | 1m58s | 7.9k | $0.44 | $0.022 |
| tencent/hy4-preview | 2026-08-28 | 56 | 56.0% | 14 | 60/80 | 10 | 0 | 5m39s | 18.1k | $0.89 | $0.045 |
| qwen/qwen3.8-27b | 2026-09-02 | 54 | 54.0% | 10 | 54/80 | 10 | 1 | 4m20s | 19.4k | $0.76 | $0.038 |
| inception/mercury-2.5-preview | 2026-09-01 | 45 | 45.0% | 8 | 47/80 | 6 | 0 | 8s | 5.9k | $0.01 | $0.001 |
| inception/mercury-2 | 2026-07-22 | 39 | 39.0% | 4 | 29/80 | 14 | 3 | 4s | 2.6k | $0.03 | $0.002 |
| qwen/qwen3-max-thinking | 2026-07-23 | 35 | 35.0% | 10 | 43/80 | 2 | 7 | 15m58s | 41.7k | $2.49 | $0.125 |
| ibm-granite/granite-4.2-8b | 2026-09-01 | 25 | 25.0% | 0 | 11/80 | 14 | 1 | 11s | 2.7k | $0.01 | $0.000 |
| nvidia/nemotron-3.5-lightning | 2026-09-01 | 20 | 20.0% | 2 | 16/80 | 6 | 11 | 7m51s | 60.6k | $0.18 | $0.009 |
| poolside/laguna-xs-2.1 | 2026-07-22 | 17 | 17.0% | 2 | 17/80 | 2 | 5 | 1m59s | 19.4k | $0.05 | $0.002 |
| upstage/solar-pro4 | 2026-09-01 | 16 | 16.0% | 3 | 17/80 | 2 | 13 | 3m34s | 41.9k | $0.05 | $0.003 |
| ibm-granite/granite-4.1-8b | 2026-09-02 | 13 | 13.0% | 0 | 9/80 | 4 | 1 | 8s | 1.7k | $0 | $0.000 |