Noometry

Model comparison

Kimi K2.5 vs Qwen2.5-Max

Kimi K2.5 is the stronger model overall, scoring 48.1 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

Kimi K2.5 Moonshot AI

48.1

Rank #57 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 35.3.
  • Kimi K2.5 has downloadable open weights; the other is API-only.

Side by side

Kimi K2.5Qwen2.5-Max
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index48.140.7
Released2026-01-272025-01-25
WeightsOpenProprietary
Context window262K—
Max output262K—
Input $ / M tokens$0.45—
Output $ / M tokens$2.25—
Results tracked5127

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), Qwen2.5-Max: 41.8 (#117)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Coding14741359
SWE-bench Verified73.8%—
SWE-bench Verified (bash only)70.8%—
LMArena WebDev1437—
SWE-bench Multilingual67.3%—
SciCode49%—
WeirdML45.6%—
LiveBench Coding—64.4%
ALE-Bench821.65—

Agentic & Tool Use Not comparable

Kimi K2.5: 34.2 (#48), Qwen2.5-Max: —

BenchmarkKimi K2.5Qwen2.5-Max
Terminal-Bench43.2%—
OSWorld63.3%—
Vending-Bench 21,198—

Reasoning Kimi K2.5 leads

Kimi K2.5: 31.2 (#80), Qwen2.5-Max: 25.6 (#147)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Hard Prompts14531360
Epoch Capabilities Index148.03132.53
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%—
LiveBench Reasoning—51.4%
LiveBench Data Analysis—67.9%
LiveBench—62.3%

Math Kimi K2.5 leads

Kimi K2.5: 51.8 (#53), Qwen2.5-Max: 36.9 (#162)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Math14701369
MathArena Final-Answer Competitions62.3%—
OTIS Mock AIME 2024-202592.2%—
LiveBench Math—58.4%
FrontierMath (Feb 2025 set)27.9%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Kimi K2.5 leads

Kimi K2.5: 53.6 (#56), Qwen2.5-Max: 35.3 (#186)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Expert14661337
GPQA Diamond87.6%—
Humanity's Last Exam24.4%—
SimpleQA Verified34.3%—
Confabulations—21.8%
Vectara Hallucination Rate14.2%—

Multimodal Not comparable

Kimi K2.5: 41.1 (#39), Qwen2.5-Max: —

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Vision1269—
LMArena Document1430—

Multilingual Kimi K2.5 leads

Kimi K2.5: 53.9 (#53), Qwen2.5-Max: 48.1 (#146)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Non-English14331352
LMArena Chinese14951382
LMArena French14541396
LMArena German14411350
LMArena Japanese14211300
LMArena Korean14101304
LMArena Russian14351353
LMArena Spanish14501377

Instruction Following Kimi K2.5 leads

Kimi K2.5: 75.3 (#64), Qwen2.5-Max: 71.3 (#152)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Instruction Following14311335
LiveBench Instruction Following—75.3%

Long Context Kimi K2.5 leads

Kimi K2.5: 52.1 (#7), Qwen2.5-Max: 41.4 (#142)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Longer Query14451358
Fiction.LiveBench86.1%—
CL-bench19.3%—
CL-bench Life13.2%—

Writing & Preference Kimi K2.5 leads

Kimi K2.5: 65.1 (#53), Qwen2.5-Max: 55.4 (#146)

BenchmarkKimi K2.5Qwen2.5-Max
LMArena Text14451367
LMArena Creative Writing14231339
LMArena Multi-Turn14441364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1579—
LiveBench Language—56.3%

Frequently asked questions

Is Kimi K2.5 better than Qwen2.5-Max?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 40.7 on the Noometry Index.

Is Kimi K2.5 or Qwen2.5-Max better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 41.8 in the Noometry coding category.

How many benchmarks do Kimi K2.5 and Qwen2.5-Max share?

18 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper