Noometry

Model comparison

Llama 3.1-70B vs MiMo-V2-Pro

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 29.6 on the Noometry Index.

Last verified . 17 shared benchmarks.

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Llama 3.1-70B scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 35.4.
  • Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 128K.
  • Llama 3.1-70B has downloadable open weights; the other is API-only.

Side by side

Llama 3.1-70BMiMo-V2-Pro
ProviderMetaXiaomi
Noometry Index29.643.0
Released2024-07-232026-03-18
WeightsOpenProprietary
Context window128K1.05M
Max output4K131K
Input $ / M tokens$0.40$0.43
Output $ / M tokens$0.40$0.87
Results tracked3523

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

Category by category

Coding MiMo-V2-Pro leads

Llama 3.1-70B: 30.3 (#296), MiMo-V2-Pro: 43.8 (#83)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Coding12601476
LMArena WebDev—1433
WeirdML9%—
BigCodeBench Instruct46.1%—
BigCodeBench Complete54.8%—
ALE-Bench—785.17

Agentic & Tool Use Not comparable

Llama 3.1-70B: 25.1 (#112), MiMo-V2-Pro: —

BenchmarkLlama 3.1-70BMiMo-V2-Pro
TheAgentCompany6.9%—
BALROG27.9%—

Reasoning Too close to call

Llama 3.1-70B: 21.6 (#220), MiMo-V2-Pro: 22.1 (#206)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Hard Prompts12411457
NYT Connections (extended)—25.8%
Thematic Generalization—45.9%
DTBench60%—
LMCA14.8%—
Epoch Capabilities Index125.92—

Math MiMo-V2-Pro leads

Llama 3.1-70B: 13.5 (#304), MiMo-V2-Pro: 39.5 (#102)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Math12521447
OTIS Mock AIME 2024-20253.6%—
Omni-MATH21%—
MATH Level 536.7%—

Knowledge MiMo-V2-Pro leads

Llama 3.1-70B: 24.2 (#269), MiMo-V2-Pro: 41.4 (#111)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Expert12091478
GPQA Diamond44.2%—
MMLU-Pro65.3%—
GPQA (HELM)42.6%—
MMLU80.1%—

Multilingual MiMo-V2-Pro leads

Llama 3.1-70B: 38.8 (#225), MiMo-V2-Pro: 52.7 (#81)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Non-English12191416
LMArena Chinese12151456
LMArena French12611469
LMArena German12221417
LMArena Japanese11321366
LMArena Korean11401400
LMArena Russian12341427
LMArena Spanish12531457

Instruction Following MiMo-V2-Pro leads

Llama 3.1-70B: 65.3 (#223), MiMo-V2-Pro: 76.0 (#49)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Instruction Following12311445
IFEval82.1%—

Long Context MiMo-V2-Pro leads

Llama 3.1-70B: 37.6 (#214), MiMo-V2-Pro: 41.5 (#138)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Longer Query12411455
CL-bench—15.7%
CL-bench Life—6.9%

Writing & Preference MiMo-V2-Pro leads

Llama 3.1-70B: 35.4 (#267), MiMo-V2-Pro: 62.8 (#70)

BenchmarkLlama 3.1-70BMiMo-V2-Pro
LMArena Text12611436
LMArena Creative Writing12321415
LMArena Multi-Turn12561456
EQ-Bench Creative Writing784—
WildBench75.8%—

Frequently asked questions

Is Llama 3.1-70B better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 29.6 on the Noometry Index.

Which is cheaper, Llama 3.1-70B or MiMo-V2-Pro?

Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.

Is Llama 3.1-70B or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 30.3 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 128K.

How many benchmarks do Llama 3.1-70B and MiMo-V2-Pro share?

17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and MiMo-V2-Pro has 23.

Related comparisons

Go deeper