Skip to main content

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 0 rows, laguna-xs-2.1 leads 7.

gemma-4-31b-itMetriclaguna-xs-2.1
google UnstableStatusServing poolside
31Score●90
33.3%Uptime●100%
59.1 sFirst token (median)●171 ms
66.2 sFull reply (median)●4.91 s
40.6 sBest reply●2.07 s
20.5 tok/sThroughput (median)●31.0 tok/s
0Round wins0
#11Leaderboard rank●#5
0%Faster when both answered (4 rounds)100%

marks the better value in each row

Full reply time overlay

Each probe, both models on one axis. Lower is better.

gemma-4-31b-itlaguna-xs-2.1 no answer
0 ms50.0 s100.0 s150.0 s200.0 s11-17 10:4311-17 16:13 UTC

Win timeline

Per round, oldest left: which model replied faster.

Agemma-4-31b-it Blaguna-xs-2.1 ·neither answered