Noometry

Model comparison

Kimi K2.5 vs Qwen3 Max

Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.7 on the Noometry Index.

Last verified . 28 shared benchmarks.

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Qwen3 Max in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.5 leads 51.8 to 38.7.
  • The biggest single-benchmark swing is NYT Connections (extended): 69.9% for Kimi K2.5 and 30.1% for Qwen3 Max.
  • Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Kimi K2.5Qwen3 Max
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index48.143.7
Released2026-01-272025-09-23
WeightsOpenProprietary
Context window262K262K
Max output262K66K
Input $ / M tokens$0.45$1.20
Output $ / M tokens$2.25$6
Results tracked5133

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

Category by category

Coding Kimi K2.5 leads

Kimi K2.5: 48.8 (#53), Qwen3 Max: 43.0 (#93)

BenchmarkKimi K2.5Qwen3 Max
LMArena Coding14741456
ALE-Bench821.65370.45
SWE-bench Verified73.8%—
SWE-bench Verified (bash only)70.8%—
LMArena WebDev1437—
SWE-bench Multilingual67.3%—
SciCode49%—
WeirdML45.6%—

Agentic & Tool Use Not comparable

Kimi K2.5: 34.2 (#48), Qwen3 Max: —

BenchmarkKimi K2.5Qwen3 Max
Vending-Bench 21,19871.56
Terminal-Bench43.2%—
OSWorld63.3%—

Reasoning Kimi K2.5 leads

Kimi K2.5: 31.2 (#80), Qwen3 Max: 22.6 (#190)

BenchmarkKimi K2.5Qwen3 Max
Kagi LLM Benchmark78.5%72.5%
NYT Connections (extended)69.9%30.1%
Chess Puzzles12%4%
LMArena Hard Prompts14531448
Epoch Capabilities Index148.03142.38
ARC-AGI-211.8%—
SimpleBench46.8%—
ARC-AGI-165.3%—
CritPt3.1%—
EnigmaEval3.4%—
Thematic Generalization69.4%—
Mystery Game Puzzles—5%
DTBench—82.1%
LMCA—28.3%

Math Kimi K2.5 leads

Kimi K2.5: 51.8 (#53), Qwen3 Max: 38.7 (#131)

BenchmarkKimi K2.5Qwen3 Max
OTIS Mock AIME 2024-202592.2%73.3%
LMArena Math14701446
FrontierMath (Tiers 1-3)—18.9%
MathArena Final-Answer Competitions62.3%—
MATH Level 5—97.1%
FrontierMath (Feb 2025 set)27.9%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Kimi K2.5 leads

Kimi K2.5: 53.6 (#56), Qwen3 Max: 48.1 (#78)

BenchmarkKimi K2.5Qwen3 Max
GPQA Diamond87.6%72.6%
SimpleQA Verified34.3%48.7%
LMArena Expert14661455
Humanity's Last Exam24.4%—
Vectara Hallucination Rate14.2%—

Multimodal Not comparable

Kimi K2.5: 41.1 (#39), Qwen3 Max: —

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

Multilingual Too close to call

Kimi K2.5: 53.9 (#53), Qwen3 Max: 53.7 (#62)

BenchmarkKimi K2.5Qwen3 Max
LMArena Non-English14331429
LMArena Chinese14951478
LMArena French14541449
LMArena German14411463
LMArena Japanese14211397
LMArena Korean14101399
LMArena Russian14351428
LMArena Spanish14501462

Instruction Following Too close to call

Kimi K2.5: 75.3 (#64), Qwen3 Max: 74.8 (#87)

BenchmarkKimi K2.5Qwen3 Max
LMArena Instruction Following14311419

Long Context Kimi K2.5 leads

Kimi K2.5: 52.1 (#7), Qwen3 Max: 41.6 (#134)

BenchmarkKimi K2.5Qwen3 Max
Fiction.LiveBench86.1%66.7%
CL-bench19.3%14.5%
LMArena Longer Query14451438
CL-bench Life13.2%—

Writing & Preference Kimi K2.5 leads

Kimi K2.5: 65.1 (#53), Qwen3 Max: 62.4 (#76)

BenchmarkKimi K2.5Qwen3 Max
LMArena Text14451439
LMArena Creative Writing14231402
LMArena Multi-Turn14441446
EQ-Bench Creative Writing1579—

Frequently asked questions

Is Kimi K2.5 better than Qwen3 Max?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.7 on the Noometry Index.

Which is cheaper, Kimi K2.5 or Qwen3 Max?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Qwen3 Max lists at $1.20 and $6.

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

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 43.0 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

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

28 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper