Noometry

Model comparison

Kimi K2.5 vs Qwen3.5 Max Preview

Kimi K2.5 is the stronger model overall, scoring 47.8 to 44.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Kimi K2.5 Moonshot AI

47.8

Rank #50 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

44.7

Rank #72 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Kimi K2.5 scores higher in 5 categories and Qwen3.5 Max Preview in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.5 leads 50.3 to 37.3.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Kimi K2.5Qwen3.5 Max Preview
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index47.844.7
Released2026-01-27—
WeightsOpenProprietary
Context window262K—
Max output262K—
Input $ / M tokens$0.45—
Output $ / M tokens$2.25—
Results tracked5117

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

Category by category

Coding Kimi K2.5 leads

Kimi K2.5: 48.7 (#48), Qwen3.5 Max Preview: 43.4 (#79)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Coding14741488
SWE-bench Verified73.8%—
SWE-bench Verified (bash only)70.8%—
LMArena WebDev1436—
SWE-bench Multilingual67.3%—
SciCode49%—
WeirdML45.6%—
ALE-Bench821.65—

Agentic & Tool Use Not comparable

Kimi K2.5: 34.0 (#44), Qwen3.5 Max Preview: —

BenchmarkKimi K2.5Qwen3.5 Max Preview
Terminal-Bench43.2%—
OSWorld63.3%—
Vending-Bench 21,198—

Reasoning Kimi K2.5 leads

Kimi K2.5: 31.2 (#74), Qwen3.5 Max Preview: 29.6 (#81)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Hard Prompts14541483
ARC-AGI-211.8%—
SimpleBench46.8%—
Kagi LLM Benchmark78.5%—
NYT Connections (extended)69.9%—
ARC-AGI-165.3%—
CritPt3.1%—
Chess Puzzles12%—
EnigmaEval3.4%—
Thematic Generalization69.4%—
Epoch Capabilities Index148.05—

Math Kimi K2.5 leads

Kimi K2.5: 50.3 (#46), Qwen3.5 Max Preview: 37.3 (#99)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Math14701473
MathArena Final-Answer Competitions62.3%—
OTIS Mock AIME 2024-202592.2%—
FrontierMath (Feb 2025 set)27.9%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Kimi K2.5 leads

Kimi K2.5: 53.6 (#52), Qwen3.5 Max Preview: 41.1 (#104)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Expert14661489
GPQA Diamond87.6%—
Humanity's Last Exam24.4%—
SimpleQA Verified34.3%—
Vectara Hallucination Rate14.2%—

Multimodal Not comparable

Kimi K2.5: 40.4 (#37), Qwen3.5 Max Preview: —

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Vision1269—
LMArena Document1430—

Multilingual Qwen3.5 Max Preview leads

Kimi K2.5: 54.1 (#50), Qwen3.5 Max Preview: 56.4 (#21)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Non-English14331465
LMArena Chinese14951534
LMArena French14541483
LMArena German14411487
LMArena Japanese14221497
LMArena Korean14121438
LMArena Russian14361472
LMArena Spanish14501470

Instruction Following Qwen3.5 Max Preview leads

Kimi K2.5: 75.5 (#60), Qwen3.5 Max Preview: 77.2 (#28)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Instruction Following14311467

Long Context Kimi K2.5 leads

Kimi K2.5: 52.1 (#7), Qwen3.5 Max Preview: 45.2 (#44)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Longer Query14451477
Fiction.LiveBench86.1%—
CL-bench19.3%—
CL-bench Life13.2%—

Writing & Preference Too close to call

Kimi K2.5: 65.3 (#51), Qwen3.5 Max Preview: 66.1 (#39)

BenchmarkKimi K2.5Qwen3.5 Max Preview
LMArena Text14451471
LMArena Creative Writing14231464
LMArena Multi-Turn14441478
EQ-Bench Creative Writing1579—

Frequently asked questions

Is Kimi K2.5 better than Qwen3.5 Max Preview?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 44.7 on the Noometry Index.

Is Kimi K2.5 or Qwen3.5 Max Preview better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 43.4 in the Noometry coding category.

How many benchmarks do Kimi K2.5 and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper