cweill/gotests
Automatically generate Go test boilerplate from your source code.
603
Generated Behavioral Tests
94.7%
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) | 94.7% | $59.14 | 366 | trace → |
| 2 | |
Claude Opus 4.8 (xhigh) | 83.3% | $30.39 | 189 | trace → |
| 3 |  |
GPT 5.5 (high) | 71.0% | $4.40 | 48 | trace → |
| 4 | |
GPT-5.6 Sol | 65.7% | $1.57 | 24 | trace → |
| 5 | |
GPT 5.5 (xhigh) | 62.2% | $7.99 | 102 | trace → |
| 6 | |
GPT-5.6 Sol (xhigh) | 61.9% | $7.87 | 70 | trace → |
| 7 | |
Claude Opus 4.6 | 61.9% | $14.13 | 274 | trace → |
| 8 | |
Claude Opus 4.7 | 61.0% | $4.87 | 105 | trace → |
| 9 |  |
Gemini 3.7 Flash | 59.9% | $1.85 | 134 | trace → |
| 10 | |
Claude Opus 4.7 (xhigh) | 52.6% | $15.81 | 190 | trace → |
| 11 | |
Claude Sonnet 4.6 | 52.2% | $31.36 | 542 | trace → |
| 12 |  |
GLM-5.2 | 51.7% | $31.94 | 294 | trace → |
| 13 | |
Gemini 3.6 Flash | 51.6% | $3.67 | 170 | trace → |
| 14 | |
GPT 5.5 | 50.9% | $1.57 | 25 | trace → |
| 15 | |
GPT 5.4 | 45.1% | $0.59 | 16 | trace → |
| 16 | |
Gemini 3.5 Flash | 44.6% | $5.46 | 175 | trace → |
| 17 | |
Gemini 3 Flash | 36.7% | $0.53 | 117 | trace → |
| 18 | |
Claude Haiku 4.5 | 33.0% | $1.18 | 135 | trace → |
| 19 | |
GPT 5.4 mini | 25.0% | $0.04 | 12 | trace → |
| 20 | |
Gemini 3.1 Pro | 21.2% | $1.22 | 51 | trace → |
| 21 | |
GPT 5 mini | 18.1% | $0.01 | 8 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run