Includes 693 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
muse-glimmer-30b leads 7 rows, deepseek-v4.1-flash leads 0.
| muse-glimmer-30b | Metric | deepseek-v4.1-flash |
|---|---|---|
| meta Serving | Status | Not served deepseek |
| 65● | Score | 0 |
| 92.3%● | Uptime | 0% |
| 26.4 s● | First token (median) | n/a |
| 52.4 s● | Full reply (median) | n/a |
| 19.6 s● | Best reply | n/a |
| 8.2 tok/s● | Throughput (median) | n/a |
| 0 | Round wins | 0 |
| #9● | Leaderboard rank | #12 |
| n/a | Faster when both answered (0 rounds) | n/a |
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.
AAAA·AAAAAAAA
Amuse-glimmer-30b Bdeepseek-v4.1-flash ·neither answered