Noometry

Model comparison

MiMo-V2.6-Pro vs Qwen3.8 27B

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 46.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

MiMo-V2.6-Pro Xiaomi

50.3

Rank #49 Confirmed

Qwen3.8 27B Alibaba (Qwen)

46.0

Rank #68 Confirmed

Summary

  • They share 18 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 9 categories and Qwen3.8 27B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 37.1.
  • The biggest single-benchmark swing is ProofBench: 70% for MiMo-V2.6-Pro and 16% for Qwen3.8 27B.
  • MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
  • MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 262K.

Side by side

MiMo-V2.6-ProQwen3.8 27B
ProviderXiaomiAlibaba (Qwen)
Noometry Index50.346.0
Released2026-09-212026-08-14
WeightsOpenOpen
Context window1.05M262K
Max output131K33K
Input $ / M tokens$0.43$0.99
Output $ / M tokens$0.87$1.49
Results tracked1931

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

Category by category

Coding MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 55.5 (#23), Qwen3.8 27B: 50.5 (#44)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena WebDev16291593
SciCode60.9%46.6%
LMArena Coding15341482
ALE-Bench1,158—

Agentic & Tool Use MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 37.5 (#35), Qwen3.8 27B: 32.9 (#57)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
APEX-Agents59.5%47.5%

Reasoning MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 43.1 (#50), Qwen3.8 27B: 41.0 (#54)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
CritPt26.6%5.4%
LMArena Hard Prompts15121460
ARC-AGI-2—42.4%
NYT Connections (extended)—54.5%
ARC-AGI-1—87.5%
DTBench—88%
LMCA—41.4%
Surface Evolver Bench—45%
Epoch Capabilities Index—149.38

Math MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 54.5 (#45), Qwen3.8 27B: 37.1 (#161)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
ProofBench70%16%
LMArena Math14941456

Knowledge MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 43.5 (#92), Qwen3.8 27B: 41.6 (#109)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Expert15431482

Multimodal Too close to call

MiMo-V2.6-Pro: 40.8 (#43), Qwen3.8 27B: 41.3 (#37)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Vision12641271

Multilingual MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 56.9 (#14), Qwen3.8 27B: 53.7 (#60)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Non-English14741430
LMArena Chinese15291504
LMArena Russian14801415
LMArena French—1465
LMArena German—1438
LMArena Japanese—1384
LMArena Korean—1393
LMArena Spanish—1448

Instruction Following MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 78.2 (#12), Qwen3.8 27B: 75.8 (#53)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Instruction Following14931439

Long Context MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 46.0 (#27), Qwen3.8 27B: 44.3 (#70)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Longer Query15011450

Writing & Preference MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 66.8 (#33), Qwen3.8 27B: 65.8 (#43)

BenchmarkMiMo-V2.6-ProQwen3.8 27B
LMArena Text14921441
LMArena Creative Writing14681384
LMArena Multi-Turn14641441
EQ-Bench Creative Writing—1671

Frequently asked questions

Is MiMo-V2.6-Pro better than Qwen3.8 27B?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 46.0 on the Noometry Index.

Which is cheaper, MiMo-V2.6-Pro or Qwen3.8 27B?

MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.

Is MiMo-V2.6-Pro or Qwen3.8 27B better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 50.5 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 262K.

How many benchmarks do MiMo-V2.6-Pro and Qwen3.8 27B share?

18 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen3.8 27B has 31.

Related comparisons

Go deeper