Benchmark Almanac

Baichuan-M2-32B

Baichuan-M2-32B places in the top three on AlignBench.

Baichuan Released August 10th, 2025 Family Baichuan-M2 The lab's model card Compare with others
11
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Baichuan Aug 2025

Baichuan-M2-32B

Open weights Mid-size

134.6 #231 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • HealthBench 60.1% #11 /31
  • HealthBench Hard 34.7% #10 /21
  • AIME 2025 72.9% #105 /143

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
AlignBench 8.77 #2 of 15 Lab model card
WritingBench 85.6 #4 of 14 Lab model card
IFEval 86% #74 of 135 Lab model card
Arena-Hard v2.0 45.8% #23 of 24 Lab model card
CFBench 77.6% #2 of 2 Lab model card

Math and science

BenchmarkScoreRankSource
AIME 2024 83.4% #33 of 88 Lab model card
AIME 2025 72.9% #105 of 143 Lab model card

Professional work

BenchmarkScoreRankSource
HealthBench 60.1% #11 of 31 Lab model card
HealthBench Hard 34.7% #10 of 21 Lab model card
BRIDGE 45.2 #23 of 39 Official leaderboard
HealthBench Consensus 91.5% #15 of 17 Lab model card

Its lab's numbers put it at 134.6, number 231 of 404

The Self-Reported Index fits one score to the 7 capability results Baichuan reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 130.1 to 139.2. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 2 of them aren't in the launch post.