Noometry

Model comparison

MiMo-V2-Flash vs Qwen2.5 7B Instruct

MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 29.0 on the Noometry Index.

Last verified . 0 shared benchmarks.

MiMo-V2-Flash Xiaomi

41.3

Rank #138 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • The widest gap is in math, where MiMo-V2-Flash leads 38.3 to 12.6.
  • MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
  • MiMo-V2-Flash accepts more context: 262K tokens versus 131K.

Side by side

MiMo-V2-FlashQwen2.5 7B Instruct
ProviderXiaomiAlibaba (Qwen)
Noometry Index41.329.0
Released2025-12-162024-09
WeightsOpenOpen
Context window262K131K
Max output66K8K
Input $ / M tokens$0.14$0.17
Output $ / M tokens$0.28$0.70
Results tracked2115

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

Category by category

Coding Too close to call

MiMo-V2-Flash: 36.1 (#211), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
LMArena WebDev1330—
SciCode25.9%—
BigCodeBench Instruct—37.6%
LMArena Coding1443—
BigCodeBench Complete—46.1%
ALE-Bench737.95—

Agentic & Tool Use Not comparable

MiMo-V2-Flash: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
BALROG—7.8%

Reasoning MiMo-V2-Flash leads

MiMo-V2-Flash: 24.9 (#157), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
CritPt0%—
Chess Puzzles—0%
LMArena Hard Prompts1420—
DTBench—47.7%
LMCA—6.4%
Epoch Capabilities Index—118.51

Math MiMo-V2-Flash leads

MiMo-V2-Flash: 38.3 (#139), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
OTIS Mock AIME 2024-2025—2.5%
Omni-MATH—29.4%
LMArena Math1396—

Knowledge MiMo-V2-Flash leads

MiMo-V2-Flash: 39.7 (#131), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
GPQA Diamond—35.5%
MMLU-Pro—53.9%
GPQA (HELM)—34.1%
LMArena Expert1425—
MMLU—72.9%

Multilingual Not comparable

MiMo-V2-Flash: 51.0 (#113), Qwen2.5 7B Instruct: —

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
LMArena Non-English1392—
LMArena Chinese1462—
LMArena French1429—
LMArena German1395—
LMArena Japanese1325—
LMArena Korean1358—
LMArena Russian1387—
LMArena Spanish1420—

Instruction Following MiMo-V2-Flash leads

MiMo-V2-Flash: 73.5 (#120), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1392—

Long Context Not comparable

MiMo-V2-Flash: 43.0 (#110), Qwen2.5 7B Instruct: —

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
LMArena Longer Query1409—

Writing & Preference MiMo-V2-Flash leads

MiMo-V2-Flash: 59.7 (#106), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkMiMo-V2-FlashQwen2.5 7B Instruct
LMArena Text1411—
LMArena Creative Writing1375—
WildBench—73.1%
LMArena Multi-Turn1404—

Frequently asked questions

Is MiMo-V2-Flash better than Qwen2.5 7B Instruct?

MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 29.0 on the Noometry Index.

Which is cheaper, MiMo-V2-Flash or Qwen2.5 7B Instruct?

MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.

Is MiMo-V2-Flash or Qwen2.5 7B Instruct better for coding?

They score almost the same on coding (36.1 vs 36.5); test both on your own repository before choosing.

Which has the bigger context window?

MiMo-V2-Flash does, with 262K tokens against 131K.

How many benchmarks do MiMo-V2-Flash and Qwen2.5 7B Instruct share?

0 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper