arq5x/bedtools2
bedtools - the swiss army knife for genome arithmetic
1,053
Generated Behavioral Tests
48.9%
Best Score
Claude Opus 4.8 (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 |  |
Claude Opus 4.8 (xhigh) | 48.9% | $17.50 | 144 | trace → |
| 2 |  |
GPT 5.5 (xhigh) | 46.1% | $7.07 | 60 | trace → |
| 3 | |
GPT 5.6 Sol (medium) | 39.2% | $1.11 | 14 | trace → |
| 4 | |
Claude Opus 4.6 | 38.9% | $19.07 | 293 | trace → |
| 5 | |
GPT 5.5 (high) | 38.4% | $4.38 | 41 | trace → |
| 6 |  |
GLM-5.2 | 35.6% | $22.81 | 205 | trace → |
| 7 |  |
Gemini 3.6 Flash | 35.1% | $9.48 | 213 | trace → |
| 8 | |
Gemini 3.5 Flash | 29.0% | $7.55 | 221 | trace → |
| 9 | |
GPT 5.5 | 28.8% | $2.08 | 22 | trace → |
| 10 | |
Gemini 3.1 Pro | 20.2% | $1.66 | 73 | trace → |
| 11 | |
GPT 5.4 | 16.8% | $0.34 | 7 | trace → |
| 12 | |
Gemini 3 Flash | 9.2% | $0.20 | 51 | trace → |
| 13 | |
Claude Haiku 4.5 | 6.0% | $0.78 | 133 | trace → |
| 14 | |
GPT 5 mini | 4.5% | $0.04 | 17 | trace → |
| 15 | |
GPT 5.4 mini | 4.4% | $0.06 | 9 | trace → |
| 16 | |
Claude Opus 4.7 (xhigh) | 2.1% | $2.85 | 88 | trace → |
| 17 | |
Claude Opus 4.7 | 2.1% | $1.67 | 60 | trace → |
| 18 | |
GPT 5.6 Sol (xhigh) | 0.2% | $5.54 | 27 | trace → |
| 19 | |
Claude Sonnet 4.6 | 0.2% | $24.91 | 426 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run