oppiliappan/eva
a calculator REPL, similar to bc(1)
913
Generated Behavioral Tests
98.7%
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) | 98.7% | $17.63 | 119 | trace → |
| 2 |  |
GPT 5.5 (xhigh) | 98.4% | $7.02 | 69 | trace → |
| 3 | |
GPT 5.6 Sol (xhigh) | 97.0% | $2.44 | 18 | trace → |
| 4 | |
GPT 5.5 (high) | 94.1% | $3.40 | 40 | trace → |
| 5 |  |
GLM-5.2 | 92.4% | $24.73 | 175 | trace → |
| 6 | |
GPT 5.6 Sol (medium) | 90.9% | $0.62 | 13 | trace → |
| 7 | |
Claude Opus 4.7 | 88.7% | $3.68 | 122 | trace → |
| 8 | |
Claude Opus 4.6 | 88.6% | $15.05 | 400 | trace → |
| 9 |  |
Gemini 3.6 Flash | 84.6% | $3.18 | 131 | trace → |
| 10 | |
Claude Sonnet 4.6 | 83.9% | $12.84 | 393 | trace → |
| 11 | |
GPT 5.4 | 75.8% | $0.33 | 13 | trace → |
| 12 | |
GPT 5.5 | 74.9% | $1.18 | 22 | trace → |
| 13 | |
Gemini 3.5 Flash | 73.8% | $4.93 | 212 | trace → |
| 14 | |
Gemini 3 Flash | 66.9% | $0.26 | 116 | trace → |
| 15 | |
GPT 5 mini | 60.5% | $0.04 | 23 | trace → |
| 16 | |
Claude Haiku 4.5 | 51.5% | $0.85 | 144 | trace → |
| 17 | |
GPT 5.4 mini | 44.9% | $0.06 | 8 | trace → |
| 18 | |
Claude Opus 4.7 (xhigh) | 0.5% | $22.33 | 294 | trace → |
| 19 | |
Gemini 3.1 Pro | 0.0% | $1.40 | 113 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run