Skip to content
Model Pulse

Leaderboard

MMLU-Proofficial site ↗

2 models scored · metric: accuracy. Prices are the cheapest listed across all serving providers. Cost/run and Pts/$ are priced for the chat token profile — short turns, light history, little caching — an assistant in a product.

This benchmark has not been calibrated to a token profile, so the figures use the site default. Treat the ordering as indicative rather than tuned to MMLU-Pro. Profile: 1.5k in · 500 out · 20% cache hit · 8k context.

Scores are facts as publicly reported by labs (see report links below and on each model page) and aggregated via models.dev. MMLU-Pro is maintained by its own project — Model Pulse is not affiliated with or endorsed by it.

Best value · top 2 by pts per dollar · chat profile
  1. 1.Nemotron 3 Ultra 550B A55B418,313
  2. 2.Sakana Namazu27,740
2 models
#
🥇Sakana Namazusakana
90.33
$0.95$40.326¢27,740262K
🥈Nemotron 3 Ultra 550B A55Bnvidia
86.8
$0.1$0.10.021¢418,3131.05M
1–2 of 2 models

Score reports: console.sakana.ai · huggingface.co — full source URLs are linked on each model page.

Cheapest scorer: Nemotron 3 Ultra 550B A55B at $0.1 input /M.