svenstaro/genact
🌀 A nonsense activity generator
231
Generated Behavioral Tests
86.6%
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) | 86.6% | $67.92 | 355 | trace → |
| 2 |  |
GPT-5.6 Sol (xhigh) | 74.9% | $3.29 | 26 | trace → |
| 3 |  |
GLM-5.2 | 74.9% | $56.55 | 423 | trace → |
| 4 | |
Claude Opus 4.8 (xhigh) | 73.2% | $23.01 | 185 | trace → |
| 5 | |
GPT 5.5 (xhigh) | 70.1% | $5.22 | 42 | trace → |
| 6 |  |
Gemini 3.5 Flash | 68.8% | $5.23 | 115 | trace → |
| 7 | |
Gemini 3.7 Flash | 61.9% | $2.33 | 113 | trace → |
| 8 | |
Claude Sonnet 4.6 | 58.4% | $17.93 | 298 | trace → |
| 9 | |
Claude Opus 4.6 | 52.4% | $11.11 | 158 | trace → |
| 10 | |
Gemini 3.6 Flash | 49.8% | $2.87 | 93 | trace → |
| 11 | |
Claude Opus 4.7 (xhigh) | 48.9% | $3.83 | 71 | trace → |
| 12 | |
GPT 5.5 (high) | 35.9% | $2.91 | 24 | trace → |
| 13 | |
Gemini 3.1 Pro | 35.5% | $1.25 | 44 | trace → |
| 14 | |
GPT 5.4 | 24.2% | $0.46 | 10 | trace → |
| 15 | |
GPT 5.5 | 23.4% | $0.94 | 13 | trace → |
| 16 | |
Claude Haiku 4.5 | 22.9% | $0.58 | 79 | trace → |
| 17 | |
Claude Opus 4.7 | 22.1% | $1.70 | 49 | trace → |
| 18 | |
Gemini 3 Flash | 20.8% | $0.47 | 48 | trace → |
| 19 | |
GPT-5.6 Sol | 17.7% | $0.37 | 8 | trace → |
| 20 | |
GPT 5.4 mini | 12.6% | $0.02 | 10 | trace → |
| 21 | |
GPT 5 mini | 1.7% | $0.02 | 9 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run