simeg/eureka
💡 CLI tool to input and store your ideas without leaving the terminal
344
Generated Behavioral Tests
98.5%
Best Score
GLM-5.2
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 |  |
GLM-5.2 | 98.5% | $17.60 | 230 | trace → |
| 2 |  |
GPT 5.6 Sol (xhigh) | 98.0% | $3.87 | 43 | trace → |
| 3 |  |
Claude Opus 4.7 (xhigh) | 97.4% | $19.76 | 260 | trace → |
| 4 |  |
Gemini 3.5 Flash | 97.1% | $2.77 | 130 | trace → |
| 5 | |
Claude Opus 4.8 (xhigh) | 96.2% | $10.74 | 77 | trace → |
| 6 | |
GPT 5.5 (high) | 93.6% | $2.56 | 36 | trace → |
| 7 | |
GPT 5.5 (xhigh) | 92.7% | $5.08 | 71 | trace → |
| 8 | |
Gemini 3.6 Flash | 91.9% | $3.49 | 139 | trace → |
| 9 | |
GPT 5.6 Sol (medium) | 87.8% | $1.13 | 16 | trace → |
| 10 | |
GPT 5.5 | 84.0% | $1.10 | 20 | trace → |
| 11 | |
Claude Opus 4.6 | 78.8% | $5.67 | 195 | trace → |
| 12 | |
Claude Opus 4.7 | 66.6% | $2.50 | 104 | trace → |
| 13 | |
Claude Sonnet 4.6 | 43.0% | $10.77 | 364 | trace → |
| 14 | |
Gemini 3.1 Pro | 37.2% | $1.77 | 100 | trace → |
| 15 | |
GPT 5.4 | 34.9% | $0.41 | 15 | trace → |
| 16 | |
GPT 5.4 mini | 24.4% | $0.05 | 11 | trace → |
| 17 | |
Claude Haiku 4.5 | 22.1% | $0.58 | 118 | trace → |
| 18 | |
Gemini 3 Flash | 21.2% | $0.21 | 66 | trace → |
| 19 | |
GPT 5 mini | 16.3% | $0.04 | 16 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run