JohannesKaufmann/html-to-markdown
⚙️ Convert HTML to Markdown. Even works with entire websites and can be extended through rules.
885
Generated Behavioral Tests
97.5%
Best Score
Claude Opus 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
21 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
Claude Opus 5 (xhigh) | 97.5% | $24.08 | 175 | trace → |
| 2 |  |
GPT-5.6 Sol (xhigh) | 96.2% | $7.23 | 41 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 92.8% | $7.12 | 72 | trace → |
| 4 |  |
Gemini 3.7 Flash | 89.4% | $1.40 | 114 | trace → |
| 5 | |
Gemini 3.5 Flash | 88.8% | $4.75 | 262 | trace → |
| 6 | |
GPT 5.5 (high) | 88.2% | $2.38 | 29 | trace → |
| 7 | |
Gemini 3.6 Flash | 86.2% | $3.86 | 142 | trace → |
| 8 | |
Claude Opus 4.7 | 85.5% | $3.56 | 92 | trace → |
| 9 | |
Claude Opus 4.8 (xhigh) | 84.0% | $13.28 | 140 | trace → |
| 10 | |
GPT-5.6 Sol | 83.7% | $1.29 | 21 | trace → |
| 11 | |
Claude Opus 4.6 | 83.7% | $14.48 | 363 | trace → |
| 12 | |
Claude Sonnet 4.6 | 81.9% | $18.69 | 503 | trace → |
| 13 | |
Claude Opus 4.7 (xhigh) | 81.1% | $10.37 | 209 | trace → |
| 14 | |
GPT 5.5 | 77.7% | $0.78 | 15 | trace → |
| 15 | |
GPT 5.4 | 67.2% | $0.23 | 7 | trace → |
| 16 | |
Gemini 3 Flash | 65.9% | $0.39 | 105 | trace → |
| 17 |  |
GLM-5.2 | 59.5% | $18.54 | 187 | trace → |
| 18 | |
Claude Haiku 4.5 | 47.3% | $0.72 | 111 | trace → |
| 19 | |
GPT 5.4 mini | 33.2% | $0.05 | 11 | trace → |
| 20 | |
Gemini 3.1 Pro | 1.5% | $1.38 | 113 | trace → |
| 21 | |
GPT 5 mini | 1.5% | $0.06 | 31 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run