typst/typst
A markup-based typesetting system that is powerful and easy to learn.
1,724
Generated Behavioral Tests
44.7%
Best Score
GPT 5.6 Sol (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 5.6 Sol (xhigh) | 44.7% | $5.12 | 29 | trace → |
| 2 |  |
GLM-5.2 | 42.0% | $34.69 | 276 | trace → |
| 3 | |
GPT 5.6 Sol (medium) | 34.9% | $0.66 | 10 | trace → |
| 4 |  |
Gemini 3.6 Flash | 32.7% | $2.25 | 104 | trace → |
| 5 | |
GPT 5.5 | 32.7% | $0.75 | 13 | trace → |
| 6 | |
GPT 5.4 | 28.0% | $0.39 | 11 | trace → |
| 7 |  |
Claude Haiku 4.5 | 20.6% | $0.72 | 127 | trace → |
| 8 | |
Claude Opus 4.8 (xhigh) | 16.8% | $20.14 | 159 | trace → |
| 9 | |
Gemini 3 Flash | 15.8% | $0.28 | 75 | trace → |
| 10 | |
Gemini 3.1 Pro | 15.5% | $0.67 | 44 | trace → |
| 11 | |
Claude Opus 4.7 (xhigh) | 14.4% | $5.44 | 125 | trace → |
| 12 | |
Claude Opus 4.6 | 13.3% | $4.62 | 285 | trace → |
| 13 | |
Claude Opus 4.7 | 11.7% | $1.51 | 50 | trace → |
| 14 | |
GPT 5 mini | 3.8% | $0.02 | 8 | trace → |
| 15 | |
GPT 5.5 (xhigh) | 3.7% | $10.06 | 83 | trace → |
| 16 | |
Gemini 3.5 Flash | 3.2% | $2.50 | 93 | trace → |
| 17 | |
GPT 5.4 mini | 2.7% | $0.03 | 7 | trace → |
| 18 | |
GPT 5.5 (high) | 1.3% | $3.71 | 32 | trace → |
| 19 | |
Claude Sonnet 4.6 | 0.0% | $52.50 | 855 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run