sharkdp/hyperfine
A command-line benchmarking tool
291
Generated Behavioral Tests
96.9%
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
17 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
Claude Opus 5 (xhigh) | 96.9% | $42.53 | 261 | trace → |
| 2 |  |
GPT 5.5 (high) | 77.0% | $2.48 | 25 | trace → |
| 3 | |
GPT 5.5 | 49.1% | $1.37 | 18 | trace → |
| 4 | |
GPT 5.4 | 48.8% | $0.25 | 9 | trace → |
| 5 |  |
Gemini 3.1 Pro | 43.6% | $1.29 | 55 | trace → |
| 6 | |
Claude Haiku 4.5 | 24.1% | $0.58 | 85 | trace → |
| 7 | |
GPT 5.4 mini | 7.2% | $0.05 | 10 | trace → |
| 8 | |
GPT 5 mini | 4.5% | $0.02 | 9 | trace → |
| 9 | |
GPT-5.6 Sol (xhigh) | 0.0% | $3.73 | 23 | trace → |
| 10 | |
GPT 5.5 (xhigh) | 0.0% | $13.44 | 107 | trace → |
| 11 | |
Gemini 3.6 Flash | 0.0% | $6.36 | 195 | trace → |
| 12 | |
Claude Opus 4.8 (xhigh) | 0.0% | $16.99 | 115 | trace → |
| 13 | |
Claude Opus 4.7 | 0.0% | $1.55 | 41 | trace → |
| 14 | |
Claude Opus 4.6 | 0.0% | $13.58 | 265 | trace → |
| 15 | |
Claude Sonnet 4.6 | 0.0% | $31.21 | 546 | trace → |
| 16 | |
Gemini 3 Flash | 0.0% | $0.27 | 68 | trace → |
| 17 | |
Claude Opus 4.7 (xhigh) | n/a | $13.94 | 180 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run