paradigmxyz/solar
Blazingly fast, modular and contributor friendly Solidity compiler, written in Rust
1,978
Generated Behavioral Tests
48.1%
Best Score
GPT-5.6 Sol (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 |  |
GPT-5.6 Sol (xhigh) | 48.1% | $2.06 | 18 | trace → |
| 2 |  |
Claude Opus 4.8 (xhigh) | 47.4% | $25.00 | 193 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 47.4% | $8.25 | 79 | trace → |
| 4 | |
GPT 5.5 (high) | 46.4% | $3.03 | 36 | trace → |
| 5 |  |
Gemini 3.7 Flash | 45.3% | $1.35 | 116 | trace → |
| 6 |  |
GLM-5.2 | 45.0% | $12.60 | 155 | trace → |
| 7 | |
GPT-5.6 Sol | 44.3% | $1.13 | 18 | trace → |
| 8 | |
Claude Opus 4.6 | 43.3% | $14.23 | 245 | trace → |
| 9 | |
Claude Opus 4.7 | 43.0% | $3.30 | 98 | trace → |
| 10 | |
Claude Sonnet 4.6 | 42.9% | $15.75 | 367 | trace → |
| 11 | |
GPT 5.5 | 40.3% | $1.50 | 24 | trace → |
| 12 | |
Claude Opus 4.7 (xhigh) | 39.1% | $5.84 | 105 | trace → |
| 13 | |
Claude Haiku 4.5 | 32.5% | $0.80 | 103 | trace → |
| 14 | |
Gemini 3.1 Pro | 32.3% | $2.40 | 146 | trace → |
| 15 | |
Gemini 3 Flash | 22.3% | $0.36 | 100 | trace → |
| 16 | |
GPT 5.4 | 11.5% | $0.16 | 8 | trace → |
| 17 | |
Gemini 3.6 Flash | 6.1% | $4.96 | 151 | trace → |
| 18 | |
GPT 5 mini | 3.3% | $0.01 | 11 | trace → |
| 19 | |
Gemini 3.5 Flash | 0.5% | $1.88 | 99 | trace → |
| 20 | |
Claude Opus 5 (xhigh) | 0.0% | $7.15 | 106 | trace → |
| 21 | |
GPT 5.4 mini | 0.0% | $0.02 | 8 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run