Benchmarks / Coding
sudo L7
Uses Surge AI's published percentage score across 60 expert-authored engineering tasks. Score: score. Collected by Jake Boggs' benchmark dashboard.
sudo L7
Higher is better · best effort per model
full table below
| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Opus 5.5 | max | 45.0% |
| 2 | Sonnet 5.5 | max | 45.0% |
| 3 | GPT-6 Astra | max | 32.2% |
| 4 | GPT-6.1 Sol | max | 31.7% |
| 5 | Fable 5.1 | max | 27.2% |
| 6 | Qwen 3.8 Max | xhigh | 15.6% |
| 7 | GLM 5.3 | max | 15.0% |
| 8 | Kimi K3 | max | 13.9% |
| 9 | Mistral Large 4 | high | 13.3% |
| 10 | Muse Spark 1.3 | max | 12.2% |
| 11 | Gemini 3.8 Flash | high | 10.6% |
| 12 | Grok 4.7 | xhigh | 10.6% |