madler/pigz
A parallel implementation of gzip for modern multi-processor, multi-core machines.
831
Generated Behavioral Tests
94.9%
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
18 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.5 (xhigh) | 94.9% | $10.57 | 91 | trace → |
| 2 | |
GPT 5.6 Sol (xhigh) | 93.6% | $4.26 | 36 | trace → |
| 3 |  |
Claude Opus 4.7 (xhigh) | 92.2% | $8.06 | 152 | trace → |
| 4 | |
GPT 5.6 Sol (medium) | 90.6% | $1.02 | 22 | trace → |
| 5 | |
GPT 5.5 (high) | 89.4% | $2.86 | 38 | trace → |
| 6 |  |
Gemini 3.5 Flash | 85.1% | $3.72 | 161 | trace → |
| 7 | |
GPT 5.5 | 84.2% | $1.03 | 17 | trace → |
| 8 | |
Claude Opus 4.7 | 83.2% | $4.53 | 149 | trace → |
| 9 |  |
GLM-5.2 | 80.6% | $39.11 | 213 | trace → |
| 10 | |
GPT 5.4 | 79.1% | $0.23 | 10 | trace → |
| 11 | |
Claude Sonnet 4.6 | 74.8% | $11.64 | 343 | trace → |
| 12 | |
Claude Haiku 4.5 | 73.4% | $0.47 | 84 | trace → |
| 13 | |
Gemini 3.1 Pro | 66.4% | $1.10 | 88 | trace → |
| 14 | |
Claude Opus 4.8 (xhigh) | 47.9% | $21.11 | 140 | trace → |
| 15 | |
Gemini 3 Flash | 29.6% | $0.14 | 37 | trace → |
| 16 | |
GPT 5 mini | 10.6% | $0.01 | 8 | trace → |
| 17 | |
Claude Opus 4.6 | 0.0% | $1.63 | 215 | trace → |
| 18 | |
GPT 5.4 mini | 0.0% | $0.02 | 13 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run