Noometry

Model comparison

MiMo-V2.5-Pro vs Qwen3 Max

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.7 on the Noometry Index.

Last verified . 21 shared benchmarks.

MiMo-V2.5-Pro Xiaomi

45.2

Rank #74 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 21 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 7 categories and Qwen3 Max in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 42.2.
  • MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 262K.
  • MiMo-V2.5-Pro has downloadable open weights; the other is API-only.

Side by side

MiMo-V2.5-ProQwen3 Max
ProviderXiaomiAlibaba (Qwen)
Noometry Index45.243.7
Released2026-04-222025-09-23
WeightsOpenProprietary
Context window1.05M262K
Max output131K66K
Input $ / M tokens$0.43$1.20
Output $ / M tokens$0.87$6
Results tracked2733

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

Category by category

Coding MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 47.4 (#60), Qwen3 Max: 43.0 (#93)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Coding15031456
ALE-Bench899.8370.45
LMArena WebDev1479—
SciCode50.2%—

Agentic & Tool Use Not comparable

MiMo-V2.5-Pro: —, Qwen3 Max: —

BenchmarkMiMo-V2.5-ProQwen3 Max
Vending-Bench 2—71.56

Reasoning MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 26.8 (#130), Qwen3 Max: 22.6 (#190)

BenchmarkMiMo-V2.5-ProQwen3 Max
NYT Connections (extended)34.4%30.1%
LMArena Hard Prompts14881448
DTBench84.5%82.1%
LMCA29.5%28.3%
Kagi LLM Benchmark—72.5%
CritPt4%—
Chess Puzzles—4%
Mystery Game Puzzles—5%
Epoch Capabilities Index—142.38

Math MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 40.0 (#96), Qwen3 Max: 38.7 (#131)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Math14811446
FrontierMath (Tiers 1-3)—18.9%
OTIS Mock AIME 2024-2025—73.3%
ProofBench22%—
MATH Level 5—97.1%

Knowledge Qwen3 Max leads

MiMo-V2.5-Pro: 42.2 (#98), Qwen3 Max: 48.1 (#78)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Expert15031455
GPQA Diamond—72.6%
SimpleQA Verified—48.7%

Multilingual MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 55.1 (#34), Qwen3 Max: 53.7 (#62)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Non-English14491429
LMArena Chinese15071478
LMArena French14881449
LMArena German14581463
LMArena Japanese14121397
LMArena Korean14371399
LMArena Russian14501428
LMArena Spanish14711462

Instruction Following MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 77.5 (#21), Qwen3 Max: 74.8 (#87)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Instruction Following14771419

Long Context MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 45.4 (#37), Qwen3 Max: 41.6 (#134)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Longer Query14831438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 65.3 (#49), Qwen3 Max: 62.4 (#76)

BenchmarkMiMo-V2.5-ProQwen3 Max
LMArena Text14651439
LMArena Creative Writing14401402
LMArena Multi-Turn14771446
EQ-Bench Creative Writing1493—
EQ-Bench 41208—

Frequently asked questions

Is MiMo-V2.5-Pro better than Qwen3 Max?

MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.7 on the Noometry Index.

Which is cheaper, MiMo-V2.5-Pro or Qwen3 Max?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is MiMo-V2.5-Pro or Qwen3 Max better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 43.0 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 262K.

How many benchmarks do MiMo-V2.5-Pro and Qwen3 Max share?

21 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper