Qwen3.8 Max
qwen3-8-max · 6 samples · combined / raw
Cost per task over time
Time per task over time
| Run? | Fetched? | Score? | Quality? | Cost/task? | Time/task? | Intel? | Code? | Agent? | MMMU%? |
|---|---|---|---|---|---|---|---|---|---|
| #1396 | 2026-08-04 01:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |
| #1395 | 2026-08-04 00:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |
| #1394 | 2026-08-03 23:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |
| #1393 | 2026-08-03 22:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |
| #1392 | 2026-08-03 21:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |
| #1391 | 2026-08-03 20:00:05 | 57.4 | 57.4 | $1.76 | 11.6m | 53.4 | 68.9 | 49.9 | 82.6 |