# SWE-bench Verified → AA-SciCode

Calibration · https://benchgap.net/calibration/1475 · data retrieved 2026-10-29

AA-SciCode is estimated from SWE-bench Verified with a Michaelis–Menten curve fitted on 34 models measured on both: y = 2.0000·x / (2.51037 + x), R² = 0.75, cross-validated error 3.9 pp. It is used for 41 estimates.

| Estimated model | SWE-bench Verified | AA-SciCode | Source |
|---|---|---|---|
| [BTL-4](https://benchgap.net/model/btl-4.md) | 78.4% | 47.6% | estimated ± 3.9 pp, high confidence |
| [MiMo-V2-Pro](https://benchgap.net/model/mimo-v2-pro.md) | 78.0% | 47.4% | estimated ± 3.9 pp, high confidence |
| [Claude Sonnet 4.5](https://benchgap.net/model/claude-sonnet-4-5.md) | 77.2% | 47.0% | estimated ± 3.9 pp, high confidence |
| [MiMo-V2-Omni](https://benchgap.net/model/mimo-v2-omni.md) | 74.8% | 45.9% | estimated ± 3.9 pp, high confidence |
| [Claude 4.1 Opus](https://benchgap.net/model/claude-4-1-opus.md) | 74.5% | 45.8% | estimated ± 3.9 pp, high confidence |
| [Step 3.5 Flash](https://benchgap.net/model/step-3-5-flash.md) | 74.4% | 45.7% | estimated ± 3.9 pp, high confidence |
| [Flint](https://benchgap.net/model/flint-40b-a2-5b.md) | 74.2% | 45.6% | estimated ± 3.9 pp, high confidence |
| [Claude Haiku 4.5](https://benchgap.net/model/claude-haiku-4-5.md) | 73.3% | 45.2% | estimated ± 3.9 pp, high confidence |
| [Jais-3-MoVA-36B-A4B](https://benchgap.net/model/jais-3-mova-36b-a4b.md) | 72.8% | 45.0% | estimated ± 3.9 pp, high confidence |
| [Claude 4 Sonnet](https://benchgap.net/model/claude-4-sonnet.md) | 72.7% | 44.9% | estimated ± 3.9 pp, high confidence |
| [MAI-Code-1.1-Flash](https://benchgap.net/model/mai-code-1-1-flash.md) | 72.6% | 44.9% | estimated ± 3.9 pp, high confidence |
| [Claude 4 Opus](https://benchgap.net/model/claude-4-opus.md) | 72.5% | 44.8% | estimated ± 3.9 pp, high confidence |
| [Jais-3-32B](https://benchgap.net/model/jais-3-32b.md) | 72.4% | 44.8% | estimated ± 3.9 pp, high confidence |
| [Qwen3.5-27B](https://benchgap.net/model/qwen3-5-27b.md) | 72.4% | 44.8% | estimated ± 3.9 pp, high confidence |
| [Grok Code Fast 1](https://benchgap.net/model/grok-code-fast-1.md) | 70.8% | 44.0% | estimated ± 3.9 pp, high confidence |
| [Solar Open 2](https://benchgap.net/model/solar-open-2.md) | 70.4% | 43.8% | estimated ± 3.9 pp, high confidence |
| [Jais-3-375B-A23B](https://benchgap.net/model/jais-3-375b-a23b.md) | 70.2% | 43.7% | estimated ± 3.9 pp, high confidence |
| [Jais-3-7B](https://benchgap.net/model/jais-3-7b.md) | 70.2% | 43.7% | estimated ± 3.9 pp, high confidence |
| [Qwen3-Coder 480B-A35B](https://benchgap.net/model/qwen3-coder-480b-a35b.md) | 69.6% | 43.4% | estimated ± 3.9 pp, high confidence |
| [Qwen3.5-35B-A3B](https://benchgap.net/model/qwen3-5-35b-a3b.md) | 69.2% | 43.2% | estimated ± 3.9 pp, high confidence |
| [DeepSeek V3.1](https://benchgap.net/model/deepseek-v3-1.md) | 66.0% | 41.6% | estimated ± 3.9 pp, high confidence |
| [Kimi K2](https://benchgap.net/model/kimi-k2.md) | 65.8% | 41.5% | estimated ± 3.9 pp, high confidence |
| [Claude 3.7 Sonnet](https://benchgap.net/model/claude-3-7-sonnet.md) | 62.3% | 39.8% | estimated ± 3.9 pp, high confidence |
| [Ternary Bonsai 2 27B](https://benchgap.net/model/ternary-bonsai-2-27b.md) | 60.8% | 39.0% | estimated ± 3.9 pp, high confidence |
| [Nemotron 3 Super 100B](https://benchgap.net/model/nemotron-3-super-100b.md) | 60.5% | 38.8% | estimated ± 3.9 pp, high confidence |
| [GLM-4.7-Flash](https://benchgap.net/model/glm-4-7-flash.md) | 59.2% | 38.2% | estimated ± 3.9 pp, high confidence |
| [DeepSeek-R1-0528](https://benchgap.net/model/deepseek-r1-0528.md) | 57.6% | 37.3% | estimated ± 3.9 pp, high confidence |
| [MiniMax M1 80k](https://benchgap.net/model/minimax-m1-80k.md) | 56.0% | 36.5% | estimated ± 3.9 pp, high confidence |
| [GPT-4.1](https://benchgap.net/model/gpt-4-1.md) | 54.6% | 35.7% | estimated ± 3.9 pp, high confidence |
| [ZAYA1-74B-Preview](https://benchgap.net/model/zaya1-74b-preview.md) | 53.2% | 35.0% | estimated ± 3.9 pp, high confidence |
| [o3-mini](https://benchgap.net/model/o3-mini.md) | 49.3% | 32.8% | estimated ± 3.9 pp, high confidence |
| [DeepSeek-R1](https://benchgap.net/model/deepseek-r1.md) | 49.2% | 32.8% | estimated ± 3.9 pp, high confidence |
| [Claude 3.5 Sonnet](https://benchgap.net/model/claude-3-5-sonnet.md) | 49.0% | 32.7% | estimated ± 3.9 pp, high confidence |
| [Devstral Small](https://benchgap.net/model/devstral-small.md) | 46.8% | 31.4% | estimated ± 3.9 pp, high confidence |
| [Sarvam 105B](https://benchgap.net/model/sarvam-105b.md) | 45.0% | 30.4% | estimated ± 3.9 pp, high confidence |
| [Claude 3.5 Haiku](https://benchgap.net/model/claude-3-5-haiku.md) | 40.6% | 27.8% | estimated ± 3.9 pp, medium confidence |
| [Sarvam 30B](https://benchgap.net/model/sarvam-30b.md) | 34.0% | 23.9% | estimated ± 3.9 pp, medium confidence |
| [Gemini 2.5 Flash-Lite](https://benchgap.net/model/gemini-2-5-flash-lite.md) | 31.6% | 22.4% | estimated ± 3.9 pp, medium confidence |
| [Gemini 2.0 Flash](https://benchgap.net/model/gemini-2-0-flash.md) | 21.4% | 15.7% | estimated ± 3.9 pp, medium confidence |
| [Gemini 2.0 Flash-Lite](https://benchgap.net/model/gemini-2-0-flash-lite.md) | 12.5% | 9.5% | estimated ± 3.9 pp, medium confidence |
| [Gemini 1.5 Flash](https://benchgap.net/model/gemini-1-5-flash.md) | 9.6% | 7.4% | estimated ± 3.9 pp, medium confidence |

## Fitted on

| Model | SWE-bench Verified | AA-SciCode |
|---|---|---|
| [Apodex 1.1](https://benchgap.net/model/apodex-1-1.md) | 77.7% | 45.5% |
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 95.0% | 61.0% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 88.6% | 54.4% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 96.0% | 56.4% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 85.2% | 54.3% |
| [DeepSeek V3](https://benchgap.net/model/deepseek-v3.md) | 42.0% | 35.8% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 79.0% | 50.3% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 80.6% | 51.0% |
| [Gemini 2.5 Pro](https://benchgap.net/model/gemini-2-5-pro.md) | 63.8% | 46.3% |
| [GPT-OSS 120B](https://benchgap.net/model/gpt-oss-120b.md) | 62.4% | 34.0% |
| [GPT-OSS 20B](https://benchgap.net/model/gpt-oss-20b.md) | 60.7% | 38.9% |
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 57.0% | 37.8% |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 47.7% | 31.5% |
| [Hy3 Preview](https://benchgap.net/model/hy3-preview.md) | 74.4% | 48.6% |
| [Inkling](https://benchgap.net/model/inkling.md) | 77.6% | 47.0% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 80.2% | 49.7% |
| [K-EXAONE 2.0](https://benchgap.net/model/k-exaone-2-0.md) | 68.2% | 42.0% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 80.2% | 51.5% |
| [MiniCPM5-2B](https://benchgap.net/model/minicpm5-2b.md) | 46.4% | 26.3% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 80.5% | 47.1% |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 77.6% | 40.2% |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 76.0% | 44.9% |
| [Nemotron 3.5 Lightning 30B A3B NVFP4](https://benchgap.net/model/nemotron-3-5-lightning-30b-a3b-nvfp4.md) | 52.8% | 32.1% |
| [Nemotron 3.5 Super VL 120B A12B](https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b.md) | 71.1% | 47.8% |
| [Nemotron 3.5 Super VL 120B A12B NVFP4](https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b-nvfp4.md) | 71.1% | 47.8% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 71.9% | 40.3% |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 72.0% | 39.7% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 76.2% | 44.8% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 77.2% | 42.8% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 73.4% | 36.6% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 80.4% | 49.5% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 77.7% | 46.1% |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 81.6% | 48.5% |
| [Solar Pro 4](https://benchgap.net/model/solar-pro-4.md) | 70.6% | 48.0% |