# Vals SWE-bench → FrontierSWE v2

Calibration · https://benchgap.net/calibration/1593 · data retrieved 2026-10-29

FrontierSWE v2 is estimated from Vals SWE-bench with a inverse Michaelis–Menten curve fitted on 12 models measured on both: y = 0.03090·(x − 0.0000) / (0.0000 + 1.0390 − x), R² = 0.67, cross-validated error 9.5 pp. It is used for 16 estimates.

| Estimated model | Vals SWE-bench | FrontierSWE v2 | Source |
|---|---|---|---|
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 82.0% | 11.6% | estimated ± 9.5 pp, medium confidence |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 79.6% | 10.1% | estimated ± 9.5 pp, medium confidence |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 78.8% | 9.7% | estimated ± 9.5 pp, medium confidence |
| [Kimi K2.7 Code](https://benchgap.net/model/kimi-k2-7-code.md) | 78.2% | 9.4% | estimated ± 9.5 pp, medium confidence |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 77.4% | 9.0% | estimated ± 9.5 pp, low confidence |
| [Gemini 3 Flash](https://benchgap.net/model/gemini-3-flash.md) | 75.0% | 8.0% | estimated ± 9.5 pp, low confidence |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 73.0% | 7.3% | estimated ± 9.5 pp, low confidence |
| [GPT-5.2-Codex](https://benchgap.net/model/gpt-5-2-codex.md) | 72.4% | 7.1% | estimated ± 9.5 pp, low confidence |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 71.4% | 6.8% | estimated ± 9.5 pp, low confidence |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 69.8% | 6.3% | estimated ± 9.5 pp, low confidence |
| [GLM-4.7](https://benchgap.net/model/glm-4-7.md) | 69.4% | 6.2% | estimated ± 9.5 pp, low confidence |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 69.0% | 6.1% | estimated ± 9.5 pp, low confidence |
| [Claude Haiku 4.5](https://benchgap.net/model/claude-haiku-4-5.md) | 66.6% | 5.5% | estimated ± 9.5 pp, low confidence |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 66.4% | 5.5% | estimated ± 9.5 pp, low confidence |
| [Qwen3.5 Flash](https://benchgap.net/model/qwen3-5-flash.md) | 64.4% | 5.0% | estimated ± 9.5 pp, low confidence |
| [Gemini 3.1 Flash-Lite](https://benchgap.net/model/gemini-3-1-flash-lite.md) | 62.8% | 4.7% | estimated ± 9.5 pp, low confidence |

## Fitted on

| Model | Vals SWE-bench | FrontierSWE v2 |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 95.0% | 47.0% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 97.0% | 52.0% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 80.8% | 20.3% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 80.0% | 19.6% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 95.4% | 30.2% |
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 92.0% | 18.1% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 96.2% | 32.2% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 95.6% | 25.3% |
| [Inkling](https://benchgap.net/model/inkling.md) | 77.6% | 4.1% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 93.4% | 25.9% |
| [Muse Spark 1.2](https://benchgap.net/model/muse-spark-1-2.md) | 86.6% | 12.0% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 85.6% | 15.8% |