Benchmark Almanac

MiMo-7B-RL

MiMo-7B-RL.

Xiaomi Corp Released April 29th, 2025 Family MiMo-7B The lab's model card Compare with others
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Xiaomi Corp Apr 2025

MiMo-7B-RL

Open weights Small

127.2 #298 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • SuperGPQA 40.5% #32 /35
  • LiveCodeBench v5 57.8% #32 /47
  • MMLU-Pro 58.6% #147 /167

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
DROP 78.7% #29 of 41 Lab model card
MMLU-Pro 58.6% #147 of 167 Lab model card
SuperGPQA 40.5% #32 of 35 Lab model card
AlignBench 6.90 #14 of 15 Lab model card
IFEval 61% #130 of 135 Lab model card

Math and science

BenchmarkScoreRankSource
MATH-500 95.8% #36 of 70 Lab model card
AIME 2024 68.2% #68 of 88 Lab model card
GPQA Diamond 54.4% #235 of 302 Lab model card
AIME 2025 55.4% #129 of 143 Lab model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v5 57.8% #32 of 47 Lab model card
LiveCodeBench v6 49.3% #82 of 90 Lab model card

Its lab's numbers put it at 127.2, number 298 of 404

The Self-Reported Index fits one score to the 10 capability results Xiaomi Corp 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 124.7 to 129.8. How we compute it.

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
MMLU-Pro 58.6% MMLU-Pro (EM) 58.6% Leaderboard Same

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. 1 of them isn't in the launch post.