Noometry

Model comparison

Llama 3.2 90B vs MiMo-V2-Omni

MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 27.5 on the Noometry Index.

Last verified . 1 shared benchmarks.

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

MiMo-V2-Omni Xiaomi

43.6

Rank #88 Confirmed

Summary

  • They share 1 benchmark with published results for both. Llama 3.2 90B scores higher in 0 categories and MiMo-V2-Omni in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2-Omni leads 39.1 to 11.1.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Llama 3.2 90BMiMo-V2-Omni
ProviderMetaXiaomi
Noometry Index27.543.6
Released2024-09-242026-03-18
WeightsOpenProprietary
Context window—262K
Max output—131K
Input $ / M tokens—$0.14
Output $ / M tokens—$0.28
Results tracked918

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Llama 3.2 90B: —, MiMo-V2-Omni: 43.3 (#89)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Coding—1466

Agentic & Tool Use Not comparable

Llama 3.2 90B: 30.0 (#80), MiMo-V2-Omni: —

BenchmarkLlama 3.2 90BMiMo-V2-Omni
BALROG27.3%—

Reasoning MiMo-V2-Omni leads

Llama 3.2 90B: 21.7 (#217), MiMo-V2-Omni: 29.7 (#88)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
EnigmaEval0.4%—
LMArena Hard Prompts—1445
Epoch Capabilities Index125.5—

Math MiMo-V2-Omni leads

Llama 3.2 90B: 11.1 (#308), MiMo-V2-Omni: 39.1 (#115)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
OTIS Mock AIME 2024-20252.6%—
LMArena Math—1430
MATH Level 539.4%—

Knowledge MiMo-V2-Omni leads

Llama 3.2 90B: 21.7 (#274), MiMo-V2-Omni: 40.5 (#118)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
GPQA Diamond41%—
LMArena Expert—1449
MMLU80.3%—

Multimodal MiMo-V2-Omni leads

Llama 3.2 90B: 25.4 (#124), MiMo-V2-Omni: 38.6 (#63)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Vision10001228
GeoBench52%—

Multilingual Not comparable

Llama 3.2 90B: —, MiMo-V2-Omni: 51.8 (#102)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Non-English—1404
LMArena Chinese—1465
LMArena French—1447
LMArena German—1399
LMArena Japanese—1317
LMArena Korean—1355
LMArena Russian—1412
LMArena Spanish—1434

Instruction Following Not comparable

Llama 3.2 90B: —, MiMo-V2-Omni: 75.2 (#66)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Instruction Following—1428

Long Context Not comparable

Llama 3.2 90B: —, MiMo-V2-Omni: 44.1 (#76)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Longer Query—1442

Writing & Preference Not comparable

Llama 3.2 90B: —, MiMo-V2-Omni: 61.4 (#87)

BenchmarkLlama 3.2 90BMiMo-V2-Omni
LMArena Text—1423
LMArena Creative Writing—1392
LMArena Multi-Turn—1445

Frequently asked questions

Is Llama 3.2 90B better than MiMo-V2-Omni?

MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 27.5 on the Noometry Index.

How many benchmarks do Llama 3.2 90B and MiMo-V2-Omni share?

1 benchmark has published results for both models. Llama 3.2 90B has 9 scored results on Noometry and MiMo-V2-Omni has 18.

Related comparisons

Go deeper