Noometry

Model comparison

Kimi K2 (Jul 2025) vs Qwen3.5 Max Preview

Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 40.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Kimi K2 (Jul 2025) Moonshot AI

40.9

Rank #134 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

44.7

Rank #72 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5 Max Preview leads 29.6 to 22.7.
  • Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

Side by side

Kimi K2 (Jul 2025)Qwen3.5 Max Preview
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index40.944.7
Released2025-07-12—
WeightsOpenProprietary
Context window262K—
Max output262K—
Input $ / M tokens$0.57—
Output $ / M tokens$2.30—
Results tracked4217

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

Category by category

Coding Too close to call

Kimi K2 (Jul 2025): 43.1 (#83), Qwen3.5 Max Preview: 43.4 (#79)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Coding13991488
SWE-bench Verified (bash only)63.4%—
Aider Polyglot59.1%—
GSO4.9%—
WeirdML42.8%—
ALE-Bench597.5—

Agentic & Tool Use Not comparable

Kimi K2 (Jul 2025): 32.2 (#59), Qwen3.5 Max Preview: —

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
Terminal-Bench35.7%—
Berkeley Function Calling Leaderboard59.1%—
METR Time Horizons59.2%—

Reasoning Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 22.7 (#173), Qwen3.5 Max Preview: 29.6 (#81)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Hard Prompts13841483
SimpleBench26.3%—
Kagi LLM Benchmark64.4%—
Epoch Capabilities Index146.02—
ForecastBench60.2—

Math Kimi K2 (Jul 2025) leads

Kimi K2 (Jul 2025): 40.1 (#81), Qwen3.5 Max Preview: 37.3 (#99)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Math13961473
Omni-MATH65.4%—
FrontierMath (Feb 2025 set)21.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 36.9 (#153), Qwen3.5 Max Preview: 41.1 (#104)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Expert13631489
MMLU-Pro81.9%—
Confabulations20.4%—
Vectara Hallucination Rate17.9%—
GPQA (HELM)65.3%—

Multilingual Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 49.8 (#125), Qwen3.5 Max Preview: 56.4 (#21)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Non-English13721465
LMArena Chinese14161534
LMArena French13791483
LMArena German13861487
LMArena Japanese13491497
LMArena Korean13241438
LMArena Russian13841472
LMArena Spanish13831470

Instruction Following Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 71.3 (#151), Qwen3.5 Max Preview: 77.2 (#28)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Instruction Following13471467
IFEval85%—

Long Context Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 41.2 (#140), Qwen3.5 Max Preview: 45.2 (#44)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Longer Query13531477
Fiction.LiveBench66.7%—
CL-bench17.6%—

Writing & Preference Qwen3.5 Max Preview leads

Kimi K2 (Jul 2025): 62.5 (#76), Qwen3.5 Max Preview: 66.1 (#39)

BenchmarkKimi K2 (Jul 2025)Qwen3.5 Max Preview
LMArena Text13801471
LMArena Creative Writing13491464
LMArena Multi-Turn13711478
Short-Story Creative Writing85.6%—
EQ-Bench Creative Writing1666—
WildBench86.2%—

Frequently asked questions

Is Kimi K2 (Jul 2025) better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 40.9 on the Noometry Index.

Is Kimi K2 (Jul 2025) or Qwen3.5 Max Preview better for coding?

They score almost the same on coding (43.1 vs 43.4); test both on your own repository before choosing.

How many benchmarks do Kimi K2 (Jul 2025) and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper