yassinebridi/serpl
A simple terminal UI for search and replace, ala VS Code.
417
Generated Behavioral Tests
95.0%
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) | 95.0% | $84.56 | 440 | trace → |
| 2 |  |
GPT-5.6 Sol (xhigh) | 72.9% | $7.80 | 50 | trace → |
| 3 | |
Claude Opus 4.8 (xhigh) | 69.5% | $20.65 | 180 | trace → |
| 4 | |
Claude Opus 4.7 (xhigh) | 69.1% | $2.51 | 79 | trace → |
| 5 | |
GPT 5.5 (xhigh) | 65.9% | $6.46 | 83 | trace → |
| 6 | |
GPT 5.5 (high) | 65.7% | $4.18 | 61 | trace → |
| 7 |  |
GLM-5.2 | 65.7% | $19.82 | 261 | trace → |
| 8 |  |
Gemini 3.7 Flash | 65.0% | $4.26 | 167 | trace → |
| 9 | |
Claude Opus 4.7 | 64.5% | $2.92 | 96 | trace → |
| 10 | |
GPT 5.5 | 64.5% | $0.91 | 22 | trace → |
| 11 | |
GPT-5.6 Sol | 63.3% | $0.79 | 12 | trace → |
| 12 | |
GPT 5.4 | 60.9% | $0.36 | 13 | trace → |
| 13 | |
Claude Haiku 4.5 | 57.6% | $0.64 | 95 | trace → |
| 14 | |
Gemini 3.5 Flash | 56.4% | $7.57 | 168 | trace → |
| 15 | |
Gemini 3.1 Pro | 56.1% | $5.31 | 134 | trace → |
| 16 | |
Gemini 3 Flash | 48.0% | $0.44 | 116 | trace → |
| 17 | |
GPT 5 mini | 44.1% | $0.01 | 10 | trace → |
| 18 | |
GPT 5.4 mini | 43.9% | $0.03 | 15 | trace → |
| 19 | |
Claude Opus 4.6 | 43.6% | $12.94 | 210 | trace → |
| 20 | |
Claude Sonnet 4.6 | 7.0% | $17.28 | 310 | trace → |
| 21 | |
Gemini 3.6 Flash | 6.7% | $3.44 | 139 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run