dandavison/delta
A syntax-highlighting pager for git, diff, grep, rg --json, and blame output
949
Generated Behavioral Tests
47.7%
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
19 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.6 Sol (xhigh) | 47.7% | $10.19 | 41 | trace → |
| 2 | |
GPT 5.5 (xhigh) | 39.0% | $10.75 | 65 | trace → |
| 3 |  |
Claude Sonnet 4.6 | 37.3% | $34.08 | 470 | trace → |
| 4 |  |
GLM-5.2 | 36.8% | $31.00 | 275 | trace → |
| 5 | |
Claude Opus 4.8 (xhigh) | 35.8% | $14.66 | 131 | trace → |
| 6 | |
GPT 5.5 (high) | 31.8% | $6.94 | 57 | trace → |
| 7 | |
GPT 5.5 | 30.1% | $0.96 | 14 | trace → |
| 8 | |
GPT 5.6 Sol (medium) | 29.4% | $0.93 | 10 | trace → |
| 9 | |
Claude Opus 4.7 (xhigh) | 28.1% | $1.19 | 48 | trace → |
| 10 | |
Claude Opus 4.7 | 23.1% | $0.35 | 22 | trace → |
| 11 |  |
Gemini 3 Flash | 21.3% | $0.20 | 52 | trace → |
| 12 | |
GPT 5 mini | 20.8% | $0.03 | 14 | trace → |
| 13 | |
GPT 5.4 | 17.8% | $0.23 | 7 | trace → |
| 14 | |
Claude Haiku 4.5 | 10.1% | $1.28 | 166 | trace → |
| 15 | |
Gemini 3.6 Flash | 9.6% | $3.73 | 129 | trace → |
| 16 | |
GPT 5.4 mini | 5.4% | $0.05 | 8 | trace → |
| 17 | |
Claude Opus 4.6 | 0.8% | $8.32 | 236 | trace → |
| 18 | |
Gemini 3.5 Flash | 0.7% | $1.85 | 79 | trace → |
| 19 | |
Gemini 3.1 Pro | 0.0% | $1.70 | 120 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run