Calibration
SWE-bench Pro → LiveCodeBench Pro
LiveCodeBench Pro is estimated from SWE-bench Pro with a Michaelis–Menten curve fitted on 6 models measured on both: y = 1.8827·x / (0.74902 + x), R² = 0.60, cross-validated error 6.0 pp. It is used for 67 estimates.
| Estimated model | SWE-bench Pro | LiveCodeBench Pro | Source |
|---|---|---|---|
| Atria Dawn Preview | 59.6% | 83.4% | estimated ± 6.0 pp, low confidence |
| Claude Fable 5 | 80.0% | 97.2% | estimated ± 6.0 pp, low confidence |
| Claude Fable 5.1 | 81.2% | 97.9% | estimated ± 6.0 pp, low confidence |
| Claude Mythos 5 | 80.3% | 97.4% | estimated ± 6.0 pp, low confidence |
| Claude Opus 4.5 | 57.1% | 81.4% | estimated ± 6.0 pp, low confidence |
| Claude Opus 4.7 (Adaptive) | 64.3% | 87.0% | estimated ± 6.0 pp, low confidence |
| Claude Opus 4.8 | 69.2% | 90.4% | estimated ± 6.0 pp, low confidence |
| Claude Opus 5 | 79.2% | 96.8% | estimated ± 6.0 pp, low confidence |
| Claude Opus 5.5 | 89.9% | 100.0% | estimated ± 6.0 pp, low confidence |
| Claude Sonnet 5 | 63.2% | 86.2% | estimated ± 6.0 pp, low confidence |
| Claude Sonnet 5.5 | 81.3% | 98.0% | estimated ± 6.0 pp, low confidence |
| DeepSeek V4 Flash 0731 | 52.6% | 77.7% | estimated ± 6.0 pp, low confidence |
| DeepSeek V4 Pro 0813 | 55.4% | 80.0% | estimated ± 6.0 pp, low confidence |
| dots3-note Preview | 61.0% | 84.5% | estimated ± 6.0 pp, low confidence |
| Gemini 3.5 Flash | 55.1% | 79.8% | estimated ± 6.0 pp, low confidence |
| Gemini 3.5 Flash-Lite | 54.2% | 79.0% | estimated ± 6.0 pp, low confidence |
| GLM-5 | 55.1% | 79.8% | estimated ± 6.0 pp, low confidence |
| GLM-5.1 | 58.4% | 82.5% | estimated ± 6.0 pp, low confidence |
| GLM-5.2 | 62.1% | 85.3% | estimated ± 6.0 pp, low confidence |
| GPT-5.2 | 55.6% | 80.2% | estimated ± 6.0 pp, low confidence |
| GPT-5.3 Codex | 56.8% | 81.2% | estimated ± 6.0 pp, low confidence |
| GPT-5.5 | 58.6% | 82.6% | estimated ± 6.0 pp, low confidence |
| GPT-5.6 Luna | 62.7% | 85.8% | estimated ± 6.0 pp, low confidence |
| GPT-5.6 Sol | 64.6% | 87.2% | estimated ± 6.0 pp, low confidence |
| GPT-5.6 Terra | 63.4% | 86.3% | estimated ± 6.0 pp, low confidence |
| Granite 4.2 30B | 33.3% | 57.9% | estimated ± 6.0 pp, low confidence |
| Granite 4.2 8B | 19.1% | 38.3% | estimated ± 6.0 pp, low confidence |
| Grok 4.5 | 64.7% | 87.3% | estimated ± 6.0 pp, low confidence |
| Hy4 preview | 65.7% | 88.0% | estimated ± 6.0 pp, low confidence |
| Inkling | 54.3% | 79.1% | estimated ± 6.0 pp, low confidence |
| Inkling-Small | 55.9% | 80.5% | estimated ± 6.0 pp, low confidence |
| Kimi K2.6 | 58.6% | 82.6% | estimated ± 6.0 pp, low confidence |
| Kimi K2.5 | 50.7% | 76.0% | estimated ± 6.0 pp, low confidence |
| Laguna M.1 | 49.2% | 74.6% | estimated ± 6.0 pp, low confidence |
| Laguna S 2.1 | 59.4% | 83.3% | estimated ± 6.0 pp, low confidence |
| Laguna XS.2 | 46.3% | 71.9% | estimated ± 6.0 pp, low confidence |
| Laguna XS 2.1 | 47.6% | 73.2% | estimated ± 6.0 pp, low confidence |
| Ling 3.0 Flash | 56.6% | 81.0% | estimated ± 6.0 pp, low confidence |
| LLaDA2.2-flash | 30.1% | 54.0% | estimated ± 6.0 pp, low confidence |
| LongCat-Flash-Lite-Sparse | 40.6% | 66.2% | estimated ± 6.0 pp, low confidence |
| MAI-Thinking-1 | 52.8% | 77.8% | estimated ± 6.0 pp, low confidence |
| MiMo-V2.5 | 56.1% | 80.6% | estimated ± 6.0 pp, low confidence |
| MiMo-V2.5-Pro | 57.2% | 81.5% | estimated ± 6.0 pp, low confidence |
| MiniCPM5-2B | 14.4% | 30.4% | estimated ± 6.0 pp, low confidence |
| MiniMax M2.7 | 56.2% | 80.7% | estimated ± 6.0 pp, low confidence |
| MiniMax M3 | 59.0% | 83.0% | estimated ± 6.0 pp, low confidence |
| Muse Glimmer 30B | 51.2% | 76.4% | estimated ± 6.0 pp, low confidence |
| Muse Spark 1.1 | 61.5% | 84.9% | estimated ± 6.0 pp, low confidence |
| Ornith-1.0-35B | 50.4% | 75.7% | estimated ± 6.0 pp, low confidence |
| Ornith-1.0-397B | 62.2% | 85.4% | estimated ± 6.0 pp, low confidence |
| Ornith-1.0-9B | 42.9% | 68.6% | estimated ± 6.0 pp, low confidence |
| Ornith-1.5-35B-A3B | 59.6% | 83.4% | estimated ± 6.0 pp, low confidence |
| Ornith-1.5-397B | 65.1% | 87.5% | estimated ± 6.0 pp, low confidence |
| Ornith-1.5-9B | 47.5% | 73.1% | estimated ± 6.0 pp, low confidence |
| Qwen3.5 397B | 50.9% | 76.2% | estimated ± 6.0 pp, low confidence |
| Qwen3.6-27B | 53.5% | 78.4% | estimated ± 6.0 pp, low confidence |
| Qwen3.6-35B-A3B | 49.5% | 74.9% | estimated ± 6.0 pp, low confidence |
| Qwen 3.6 Max (preview) | 57.3% | 81.6% | estimated ± 6.0 pp, low confidence |
| Qwen3.6 Plus | 56.6% | 81.0% | estimated ± 6.0 pp, low confidence |
| Qwen3.7 Max | 60.6% | 84.2% | estimated ± 6.0 pp, low confidence |
| Qwen3.7 Plus | 57.6% | 81.8% | estimated ± 6.0 pp, low confidence |
| Qwen3.8-27B | 61.7% | 85.0% | estimated ± 6.0 pp, low confidence |
| Qwen3.8-Flash-Next | 62.5% | 85.6% | estimated ± 6.0 pp, low confidence |
| Qwen3.8 Max | 67.7% | 89.4% | estimated ± 6.0 pp, low confidence |
| Qwen3.8-Omni-Flash | 63.3% | 86.2% | estimated ± 6.0 pp, low confidence |
| Beam | 65.5% | 87.8% | estimated ± 6.0 pp, low confidence |
| Step 3.7 Flash | 56.3% | 80.8% | estimated ± 6.0 pp, low confidence |