eudoxia0/hashcards
A plain text-based spaced repetition system.
1,019
Generated Behavioral Tests
92.6%
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) | 92.6% | $17.98 | 145 | trace → |
| 2 |  |
GPT 5.5 (xhigh) | 81.4% | $9.67 | 100 | trace → |
| 3 | |
GPT 5.6 Sol (xhigh) | 80.1% | $4.96 | 25 | trace → |
| 4 | |
GPT 5.5 | 79.3% | $2.18 | 28 | trace → |
| 5 | |
GPT 5.6 Sol (medium) | 74.6% | $1.24 | 20 | trace → |
| 6 |  |
GLM-5.2 | 70.9% | $24.45 | 215 | trace → |
| 7 |  |
Gemini 3.5 Flash | 61.8% | $9.93 | 235 | trace → |
| 8 | |
Gemini 3 Flash | 58.4% | $0.33 | 114 | trace → |
| 9 | |
GPT 5.5 (high) | 56.9% | $5.14 | 63 | trace → |
| 10 | |
Claude Haiku 4.5 | 55.3% | $0.82 | 141 | trace → |
| 11 | |
GPT 5.4 mini | 41.5% | $0.04 | 7 | trace → |
| 12 | |
GPT 5 mini | 38.0% | $0.04 | 25 | trace → |
| 13 | |
Gemini 3.6 Flash | 6.1% | $5.44 | 173 | trace → |
| 14 | |
Claude Opus 4.7 | 6.1% | $1.55 | 65 | trace → |
| 15 | |
Claude Sonnet 4.6 | 6.1% | $51.19 | 537 | trace → |
| 16 | |
Claude Opus 4.7 (xhigh) | 3.7% | $11.74 | 179 | trace → |
| 17 | |
GPT 5.4 | 3.7% | $0.48 | 15 | trace → |
| 18 | |
Claude Opus 4.6 | 0.0% | $6.91 | 254 | trace → |
| 19 | |
Gemini 3.1 Pro | 0.0% | $2.07 | 136 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run