rochacbruno/marmite
Markdown makes sites - A Static Site Generator for Blogs
668
Generated Behavioral Tests
68.6%
Best Score
GPT 5.5 (xhigh)
Results by Model
Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details
Per-Model Results
19 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.5 (xhigh) | 68.6% | $12.42 | 97 | trace → |
| 2 | |
GPT 5.6 Sol (xhigh) | 65.0% | $6.63 | 41 | trace → |
| 3 | |
GPT 5.5 (high) | 53.7% | $2.80 | 29 | trace → |
| 4 |  |
GLM-5.2 | 51.7% | $48.65 | 311 | trace → |
| 5 | |
GPT 5.5 | 50.3% | $1.29 | 14 | trace → |
| 6 |  |
Claude Opus 4.8 (xhigh) | 49.2% | $11.67 | 99 | trace → |
| 7 | |
GPT 5.6 Sol (medium) | 45.4% | $1.74 | 18 | trace → |
| 8 | |
Claude Opus 4.6 | 45.4% | $13.96 | 206 | trace → |
| 9 |  |
Gemini 3.5 Flash | 43.9% | $8.94 | 216 | trace → |
| 10 | |
Gemini 3.6 Flash | 28.6% | $3.97 | 126 | trace → |
| 11 | |
GPT 5 mini | 27.8% | $0.02 | 13 | trace → |
| 12 | |
Claude Opus 4.7 (xhigh) | 24.6% | $1.26 | 42 | trace → |
| 13 | |
GPT 5.4 | 22.5% | $0.33 | 11 | trace → |
| 14 | |
Gemini 3.1 Pro | 22.3% | $1.26 | 62 | trace → |
| 15 | |
Claude Opus 4.7 | 21.4% | $0.74 | 28 | trace → |
| 16 | |
Gemini 3 Flash | 18.6% | $0.35 | 79 | trace → |
| 17 | |
Claude Sonnet 4.6 | 11.2% | $57.18 | 790 | trace → |
| 18 | |
GPT 5.4 mini | 8.2% | $0.06 | 14 | trace → |
| 19 | |
Claude Haiku 4.5 | 0.0% | $0.94 | 115 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run