| Measure | Result |
|---|---|
| Requests | 666 |
| Models | 8 |
| Model-and-level configurations | 37 |
| Tasks per configuration | 6 |
| Repetitions | 3 |
| Input tokens | 317,705 |
| Output tokens | 604,142 |
| Reasoning tokens within output | 575,272 |
| Visible answer tokens | 28,870 |
| Total tokens | 921,847 |
| Estimated standard on-demand cost | $12.726352 |
| Semantically correct answers | 631 (94.7%) |
| Correct bare-JSON answers | 585 |
| Correct answers (code fenced) | 46 |
| Wrong answers | 32 |
| Truncated responses | 2 |
| Endpoint failures | 1 |
| Policy refusals | 0 |
Last active
July 31, 2026 15:45
-
-
Save garystafford/28eeca0a2e139e28c35c50d050764b66 to your computer and use it in GitHub Desktop.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment