ninja-build/ninja
a small build system with a focus on speed
1,438
Generated Behavioral Tests
90.5%
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) | 90.5% | $21.96 | 135 | trace → |
| 2 |  |
GPT 5.5 (xhigh) | 82.0% | $15.17 | 144 | trace → |
| 3 | |
GPT 5.6 Sol (xhigh) | 78.2% | $5.50 | 37 | trace → |
| 4 | |
Claude Opus 4.6 | 72.3% | $16.10 | 324 | trace → |
| 5 | |
Claude Opus 4.7 (xhigh) | 68.3% | $14.14 | 212 | trace → |
| 6 | |
Claude Sonnet 4.6 | 67.7% | $18.29 | 400 | trace → |
| 7 |  |
Gemini 3.6 Flash | 66.3% | $3.52 | 166 | trace → |
| 8 | |
GPT 5.5 (high) | 65.5% | $3.50 | 45 | trace → |
| 9 | |
GPT 5.6 Sol (medium) | 65.5% | $0.96 | 19 | trace → |
| 10 |  |
GLM-5.2 | 61.6% | $23.13 | 239 | trace → |
| 11 | |
GPT 5.5 | 57.2% | $0.90 | 15 | trace → |
| 12 | |
Gemini 3.5 Flash | 37.8% | $4.46 | 211 | trace → |
| 13 | |
Gemini 3.1 Pro | 37.1% | $0.68 | 45 | trace → |
| 14 | |
Claude Haiku 4.5 | 34.4% | $0.91 | 129 | trace → |
| 15 | |
Gemini 3 Flash | 26.1% | $0.23 | 65 | trace → |
| 16 | |
GPT 5 mini | 5.6% | $0.01 | 11 | trace → |
| 17 | |
Claude Opus 4.7 | 4.8% | $1.69 | 69 | trace → |
| 18 | |
GPT 5.4 | 3.5% | $0.20 | 9 | trace → |
| 19 | |
GPT 5.4 mini | 0.0% | $0.03 | 14 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run