YS-L/flamelens
Flamegraph viewer in the terminal
223
Generated Behavioral Tests
94.2%
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) | 94.2% | $84.97 | 330 | trace → |
| 2 |  |
GLM-5.2 | 78.5% | $36.95 | 258 | trace → |
| 3 | |
Claude Opus 4.8 (xhigh) | 76.7% | $20.34 | 157 | trace → |
| 4 |  |
GPT-5.6 Sol (xhigh) | 65.0% | $3.76 | 38 | trace → |
| 5 |  |
Gemini 3.7 Flash | 62.3% | $2.38 | 134 | trace → |
| 6 | |
GPT 5.5 (high) | 61.9% | $2.47 | 49 | trace → |
| 7 | |
Gemini 3.6 Flash | 60.1% | $4.04 | 145 | trace → |
| 8 | |
Claude Opus 4.6 | 59.2% | $15.81 | 252 | trace → |
| 9 | |
GPT 5.5 (xhigh) | 57.4% | $4.30 | 48 | trace → |
| 10 | |
Claude Sonnet 4.6 | 57.4% | $43.26 | 490 | trace → |
| 11 | |
Claude Opus 4.7 | 57.0% | $1.38 | 62 | trace → |
| 12 | |
GPT 5.5 | 55.6% | $0.95 | 14 | trace → |
| 13 | |
GPT-5.6 Sol | 53.4% | $0.83 | 16 | trace → |
| 14 | |
Gemini 3.5 Flash | 51.6% | $6.36 | 120 | trace → |
| 15 | |
Gemini 3 Flash | 43.9% | $0.19 | 57 | trace → |
| 16 | |
Claude Haiku 4.5 | 41.3% | $0.82 | 157 | trace → |
| 17 | |
GPT 5.4 | 22.0% | $0.07 | 7 | trace → |
| 18 | |
GPT 5.4 mini | 17.0% | $0.01 | 8 | trace → |
| 19 | |
Gemini 3.1 Pro | 14.8% | $2.25 | 77 | trace → |
| 20 | |
GPT 5 mini | 13.9% | $0.02 | 11 | trace → |
| 21 | |
Claude Opus 4.7 (xhigh) | 1.3% | $5.90 | 135 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run