# Vibe Code Bench → SWE-bench Pro

Calibration · https://benchgap.net/calibration/vibecodebench/current/to/swe-bench-pro/current · data retrieved 2026-11-21

SWE-bench Pro is estimated from Vibe Code Bench with a linear curve fitted on 14 models measured on both: y = 0.0873·x + 0.5259, R² = 0.34, cross-validated error 2.9 pp. It is used for 0 estimates.

## Fitted on

| Model | Vibe Code Bench | SWE-bench Pro |
|---|---|---|
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 57.6% | 53.4% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 71.0% | 64.3% |
| [DeepSeek V4 Pro](https://benchgap.net/model/deepseek-v4-pro.md) | 49.9% | 55.4% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 48.7% | 55.1% |
| [GLM-5.1](https://benchgap.net/model/glm-5-1.md) | 31.5% | 58.4% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 53.5% | 55.6% |
| [GPT-5.3 Codex](https://benchgap.net/model/gpt-5-3-codex.md) | 61.8% | 56.8% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 67.4% | 57.7% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 69.8% | 58.6% |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 4.1% | 51.8% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 37.9% | 58.6% |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 27.0% | 56.2% |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 19.7% | 52.4% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 25.6% | 56.6% |
