Noometry

Model comparison

Llama 3.1-70B vs MiMo-V2-Flash

MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Llama 3.1-70B Meta

29.4

Rank #299 Confirmed

MiMo-V2-Flash Xiaomi

40.8

Rank #137 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Llama 3.1-70B scores higher in 0 categories and MiMo-V2-Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.9 to 35.6.
  • MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
  • MiMo-V2-Flash accepts more context: 262K tokens versus 128K.

Side by side

Llama 3.1-70BMiMo-V2-Flash
ProviderMetaXiaomi
Noometry Index29.440.8
Released2024-07-232025-12-16
WeightsOpenOpen
Context window128K262K
Max output4K66K
Input $ / M tokens$0.40$0.14
Output $ / M tokens$0.40$0.28
Results tracked3521

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

Category by category

Coding MiMo-V2-Flash leads

Llama 3.1-70B: 29.8 (#292), MiMo-V2-Flash: 35.8 (#205)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Coding12601443
LMArena WebDev—1330
SciCode—25.9%
WeirdML9%—
BigCodeBench Instruct46.1%—
BigCodeBench Complete54.8%—
ALE-Bench—737.95

Agentic & Tool Use Not comparable

Llama 3.1-70B: 24.9 (#104), MiMo-V2-Flash: —

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

Reasoning MiMo-V2-Flash leads

Llama 3.1-70B: 20.8 (#215), MiMo-V2-Flash: 24.1 (#155)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Hard Prompts12411420
CritPt—0%
DTBench60%—
LMCA14.8%—
Epoch Capabilities Index125.91—

Math MiMo-V2-Flash leads

Llama 3.1-70B: 12.7 (#298), MiMo-V2-Flash: 35.6 (#141)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Math12521396
OTIS Mock AIME 2024-20253.6%—
Omni-MATH21%—
MATH Level 536.7%—

Knowledge MiMo-V2-Flash leads

Llama 3.1-70B: 24.1 (#264), MiMo-V2-Flash: 39.1 (#126)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Expert12091425
GPQA Diamond44.2%—
MMLU-Pro65.3%—
GPQA (HELM)42.6%—
MMLU80.1%—

Multilingual MiMo-V2-Flash leads

Llama 3.1-70B: 38.9 (#220), MiMo-V2-Flash: 51.1 (#109)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Non-English12191391
LMArena Chinese12151463
LMArena French12601429
LMArena German12221395
LMArena Japanese11321324
LMArena Korean11401358
LMArena Russian12341387
LMArena Spanish12531420

Instruction Following MiMo-V2-Flash leads

Llama 3.1-70B: 65.5 (#218), MiMo-V2-Flash: 73.7 (#115)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Instruction Following12311392
IFEval82.1%—

Long Context MiMo-V2-Flash leads

Llama 3.1-70B: 37.6 (#208), MiMo-V2-Flash: 43.0 (#106)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Longer Query12411409

Writing & Preference MiMo-V2-Flash leads

Llama 3.1-70B: 35.6 (#262), MiMo-V2-Flash: 59.9 (#101)

BenchmarkLlama 3.1-70BMiMo-V2-Flash
LMArena Text12611411
LMArena Creative Writing12321375
LMArena Multi-Turn12561404
EQ-Bench Creative Writing784—
WildBench75.8%—

Frequently asked questions

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

MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 29.4 on the Noometry Index.

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

MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.

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

MiMo-V2-Flash scores higher on coding benchmarks: 35.8 versus 29.8 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Flash does, with 262K tokens against 128K.

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

17 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and MiMo-V2-Flash has 21.

Related comparisons

Go deeper