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
glm-5.3-flash leads 0 rows, muse-glimmer-30b leads 7.
| glm-5.3-flash | Metric | muse-glimmer-30b |
|---|---|---|
| z Down | Status | Serving meta |
| 0 | Score | ●64 |
| 0% | Uptime | ●91.7% |
| n/a | First token (median) | ●33.4 s |
| n/a | Full reply (median) | ●61.1 s |
| n/a | Best reply | ●26.5 s |
| n/a | Throughput (median) | ●8.2 tok/s |
| 0 | Round wins | 0 |
| #15 | Leaderboard rank | ●#9 |
| 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.
BBBB·BBBBBBB
Aglm-5.3-flash Bmuse-glimmer-30b ·neither answered