lh3/seqtk
Toolkit for processing sequences in FASTA/Q formats
429
Generated Behavioral Tests
81.4%
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) | 81.4% | $6.26 | 51 | trace → |
| 2 |  |
Claude Opus 4.8 (xhigh) | 79.3% | $12.27 | 95 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 74.6% | $8.12 | 77 | trace → |
| 4 | |
Claude Opus 4.7 (xhigh) | 73.4% | $9.95 | 147 | trace → |
| 5 | |
GPT 5.5 (high) | 68.5% | $3.38 | 46 | trace → |
| 6 | |
Claude Opus 4.6 | 67.4% | $14.11 | 306 | trace → |
| 7 | |
GPT 5.6 Sol (medium) | 65.3% | $0.81 | 15 | trace → |
| 8 | |
Claude Sonnet 4.6 | 64.8% | $19.13 | 482 | trace → |
| 9 |  |
Gemini 3.6 Flash | 64.6% | $14.32 | 223 | trace → |
| 10 | |
Claude Opus 4.7 | 63.9% | $2.48 | 68 | trace → |
| 11 | |
Gemini 3.5 Flash | 63.6% | $11.52 | 270 | trace → |
| 12 | |
GPT 5.5 | 51.3% | $0.94 | 18 | trace → |
| 13 |  |
GLM-5.2 | 44.5% | $23.07 | 144 | trace → |
| 14 | |
GPT 5.4 | 40.3% | $0.26 | 12 | trace → |
| 15 | |
Gemini 3 Flash | 21.4% | $0.24 | 92 | trace → |
| 16 | |
Gemini 3.1 Pro | 20.0% | $1.26 | 125 | trace → |
| 17 | |
Claude Haiku 4.5 | 17.0% | $0.57 | 84 | trace → |
| 18 | |
GPT 5 mini | 8.9% | $0.01 | 16 | trace → |
| 19 | |
GPT 5.4 mini | 6.8% | $0.02 | 9 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run