Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.
Model comparison
Head-to-head from live probes, last 24 hours.
Head-to-head stats
gemma-4-31b-it leads 1 rows, muse-glimmer-30b leads 6.
| gemma-4-31b-it | Metric | muse-glimmer-30b |
|---|---|---|
| google Unstable | Status | Serving meta |
| 31 | Score | ●64 |
| 33.3% | Uptime | ●91.7% |
| 59.1 s | First token (median) | ●33.4 s |
| 66.2 s | Full reply (median) | ●61.1 s |
| 40.6 s | Best reply | ●26.5 s |
| 20.5 tok/s● | Throughput (median) | 8.2 tok/s |
| 0 | Round wins | 0 |
| #11 | Leaderboard rank | ●#9 |
| 50.0% | Faster when both answered (4 rounds) | 50.0% |
marks the better value in each row
Full reply time overlay
Each probe, both models on one axis. Lower is better.
Win timeline
Per round, oldest left: which model replied faster.
ABBB·BBBBABB
Agemma-4-31b-it Bmuse-glimmer-30b ·neither answered