Noometry

Model comparison

Llama 3.1-405B vs MiMo-V2-Omni

MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Llama 3.1-405B Meta

30.4

Rank #279 Confirmed

MiMo-V2-Omni Xiaomi

42.9

Rank #91 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and MiMo-V2-Omni in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2-Omni leads 61.6 to 39.1.
  • Llama 3.1-405B has downloadable open weights; the other is API-only.

Side by side

Llama 3.1-405BMiMo-V2-Omni
ProviderMetaXiaomi
Noometry Index30.442.9
Released2024-07-232026-03-18
WeightsOpenProprietary
Context window—262K
Max output—131K
Input $ / M tokens—$0.14
Output $ / M tokens—$0.28
Results tracked4218

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

Category by category

Coding MiMo-V2-Omni leads

Llama 3.1-405B: 32.7 (#257), MiMo-V2-Omni: 42.7 (#87)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Coding12911467
WeirdML21.4%—

Agentic & Tool Use Not comparable

Llama 3.1-405B: 20.9 (#131), MiMo-V2-Omni: —

BenchmarkLlama 3.1-405BMiMo-V2-Omni
TheAgentCompany7.4%—
Cybench7.5%—

Reasoning MiMo-V2-Omni leads

Llama 3.1-405B: 16.4 (#293), MiMo-V2-Omni: 28.6 (#86)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Hard Prompts12701445
SimpleBench23%—
Kagi LLM Benchmark45%—
DTBench61.4%—
BIG-Bench Hard82.9%—
Epoch Capabilities Index128.76—
ForecastBench59.9—
HellaSwag89.2%—
PIQA85.9%—
WinoGrande89.2%—

Math MiMo-V2-Omni leads

Llama 3.1-405B: 17.3 (#283), MiMo-V2-Omni: 36.4 (#112)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Math12811432
OTIS Mock AIME 2024-20259.7%—
Omni-MATH24.9%—
MATH Level 549.8%—

Knowledge MiMo-V2-Omni leads

Llama 3.1-405B: 30.4 (#221), MiMo-V2-Omni: 39.9 (#114)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Expert12431449
GPQA Diamond50.9%—
MMLU-Pro72.3%—
Confabulations17.6%—
GPQA (HELM)52.2%—
ARC (AI2) Challenge95.3%—
MMLU84.5%—
TriviaQA82.7%—

Multimodal Not comparable

Llama 3.1-405B: —, MiMo-V2-Omni: 37.9 (#62)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Vision—1228

Multilingual MiMo-V2-Omni leads

Llama 3.1-405B: 40.9 (#209), MiMo-V2-Omni: 52.0 (#97)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Non-English12481404
LMArena Chinese12421469
LMArena French12781448
LMArena German12521398
LMArena Japanese12081318
LMArena Korean11841355
LMArena Russian12651412
LMArena Spanish12591432

Instruction Following MiMo-V2-Omni leads

Llama 3.1-405B: 66.1 (#209), MiMo-V2-Omni: 75.4 (#62)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Instruction Following12591428
IFEval81.1%—

Long Context MiMo-V2-Omni leads

Llama 3.1-405B: 38.4 (#192), MiMo-V2-Omni: 44.1 (#72)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Longer Query12661442

Writing & Preference MiMo-V2-Omni leads

Llama 3.1-405B: 39.1 (#246), MiMo-V2-Omni: 61.6 (#83)

BenchmarkLlama 3.1-405BMiMo-V2-Omni
LMArena Text12841424
LMArena Creative Writing12621393
LMArena Multi-Turn12971446
EQ-Bench Creative Writing870—
WildBench78.3%—

Frequently asked questions

Is Llama 3.1-405B better than MiMo-V2-Omni?

MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 30.4 on the Noometry Index.

Is Llama 3.1-405B or MiMo-V2-Omni better for coding?

MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 32.7 in the Noometry coding category.

How many benchmarks do Llama 3.1-405B and MiMo-V2-Omni share?

17 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and MiMo-V2-Omni has 18.

Related comparisons

Go deeper