antonmedv/walk
Terminal file manager
426
Generated Behavioral Tests
94.6%
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) | 94.6% | $9.88 | 59 | trace → |
| 2 | |
GPT 5.5 (xhigh) | 92.3% | $7.96 | 55 | trace → |
| 3 | |
GPT 5.5 (high) | 87.6% | $4.11 | 45 | trace → |
| 4 |  |
Gemini 3.6 Flash | 84.7% | $3.53 | 129 | trace → |
| 5 | |
GPT 5.5 | 84.0% | $1.30 | 20 | trace → |
| 6 | |
GPT 5.6 Sol (medium) | 81.0% | $0.48 | 10 | trace → |
| 7 |  |
Claude Opus 4.7 | 79.8% | $1.65 | 70 | trace → |
| 8 | |
Claude Opus 4.8 (xhigh) | 78.5% | $32.54 | 174 | trace → |
| 9 | |
Claude Opus 4.7 (xhigh) | 76.5% | $5.10 | 118 | trace → |
| 10 | |
Claude Opus 4.6 | 59.4% | $15.76 | 297 | trace → |
| 11 | |
Gemini 3.5 Flash | 58.5% | $8.08 | 190 | trace → |
| 12 |  |
GLM-5.2 | 57.7% | $23.84 | 186 | trace → |
| 13 | |
Claude Sonnet 4.6 | 49.8% | $23.52 | 407 | trace → |
| 14 | |
Claude Haiku 4.5 | 46.0% | $0.88 | 175 | trace → |
| 15 | |
GPT 5.4 | 31.5% | $0.24 | 13 | trace → |
| 16 | |
Gemini 3 Flash | 28.9% | $0.16 | 35 | trace → |
| 17 | |
GPT 5.4 mini | 28.6% | $0.02 | 7 | trace → |
| 18 | |
GPT 5 mini | 24.6% | $0.02 | 16 | trace → |
| 19 | |
Gemini 3.1 Pro | 24.4% | $1.63 | 80 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run