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
gpt-oss-20b leads 0 rows, nemotron-3.5-bolt-e4b leads 8.
| gpt-oss-20b | Metric | nemotron-3.5-bolt-e4b |
|---|---|---|
| openai Down | Status | Serving nvidia |
| 0 | Score | ●95 |
| 0% | Uptime | ●100% |
| n/a | First token (median) | ●118 ms |
| n/a | Full reply (median) | ●1.62 s |
| n/a | Best reply | ●1.46 s |
| n/a | Throughput (median) | ●83.8 tok/s |
| 0 | Round wins | ●1 |
| #14 | Leaderboard rank | ●#2 |
| 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.
BBBBBBBBBBBB
Agpt-oss-20b Bnemotron-3.5-bolt-e4b ·neither answered