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, step-5-preview leads 7.
| gpt-oss-20b | Metric | step-5-preview |
|---|---|---|
| openai Down | Status | Unstable stepfun |
| 0 | Score | ●45 |
| 0% | Uptime | ●50.0% |
| n/a | First token (median) | ●7.49 s |
| n/a | Full reply (median) | ●25.4 s |
| n/a | Best reply | ●7.40 s |
| n/a | Throughput (median) | ●10.7 tok/s |
| 0 | Round wins | 0 |
| #14 | Leaderboard rank | ●#10 |
| 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.
B·B··BB··BB·
Agpt-oss-20b Bstep-5-preview ·neither answered