blacknon/hwatch
A modern alternative to the watch command, records the differences in execution results and can check this differences at after.
1,016
Generated Behavioral Tests
88.7%
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) | 88.7% | $16.75 | 139 | trace → |
| 2 |  |
GPT 5.6 Sol (xhigh) | 87.6% | $3.38 | 25 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 85.4% | $5.31 | 65 | trace → |
| 4 | |
GPT 5.5 (high) | 82.6% | $4.53 | 59 | trace → |
| 5 | |
Claude Opus 4.6 | 81.1% | $10.71 | 221 | trace → |
| 6 |  |
GLM-5.2 | 80.7% | $18.51 | 231 | trace → |
| 7 | |
GPT 5.5 | 79.9% | $1.67 | 23 | trace → |
| 8 | |
GPT 5.6 Sol (medium) | 78.4% | $1.07 | 16 | trace → |
| 9 |  |
Gemini 3.6 Flash | 78.0% | $3.13 | 144 | trace → |
| 10 | |
Claude Opus 4.7 | 77.3% | $1.23 | 56 | trace → |
| 11 | |
Claude Opus 4.7 (xhigh) | 76.2% | $10.58 | 210 | trace → |
| 12 | |
Gemini 3.1 Pro | 75.1% | $1.04 | 73 | trace → |
| 13 | |
Gemini 3.5 Flash | 68.4% | $6.05 | 145 | trace → |
| 14 | |
Claude Haiku 4.5 | 66.0% | $0.59 | 88 | trace → |
| 15 | |
Gemini 3 Flash | 61.0% | $0.34 | 71 | trace → |
| 16 | |
GPT 5.4 | 60.2% | $0.27 | 9 | trace → |
| 17 | |
GPT 5.4 mini | 24.7% | $0.02 | 9 | trace → |
| 18 | |
GPT 5 mini | 2.6% | $0.03 | 10 | trace → |
| 19 | |
Claude Sonnet 4.6 | 1.8% | $14.13 | 378 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run