Noometry

Model comparison

Kimi K3 vs Qwen1.5-32B

Kimi K3 is the stronger model overall, scoring 59.5 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Kimi K3 leads 63.2 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 93.1% for Kimi K3 and 30.7% for Qwen1.5-32B.

Side by side

Kimi K3Qwen1.5-32B
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index59.530.5
Released2026-07-162024-02-04
WeightsOpenOpen
Context window1.05M—
Max output1.05M—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5321

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

Category by category

Coding Kimi K3 leads

Kimi K3: 61.0 (#10), Qwen1.5-32B: 31.7 (#282)

BenchmarkKimi K3Qwen1.5-32B
LMArena Coding15081155
DeepSWE68.5%—
FrontierCode44.2%—
LMArena WebDev1654—
FrontierSWE25.9%—
SciCode59.5%—
WeirdML82.6%—
BigCodeBench Instruct—32.3%
BigCodeBench Complete—42%
ALE-Bench1,524—

Agentic & Tool Use Not comparable

Kimi K3: 41.8 (#20), Qwen1.5-32B: —

BenchmarkKimi K3Qwen1.5-32B
APEX-Agents50.6%—
τ²-bench Banking37.1%—
PostTrainBench32%—
GBAEval48.3%—
GDP.pdf19%—
Vending-Bench 25,165—

Reasoning Kimi K3 leads

Kimi K3: 63.0 (#17), Qwen1.5-32B: 21.8 (#212)

BenchmarkKimi K3Qwen1.5-32B
LMArena Hard Prompts14961130
ARC-AGI-260.4%—
SimpleBench60.7%—
NYT Connections (extended)93.6%—
ARC-AGI-194.5%—
CritPt23.4%—
Chess Puzzles39%—
Mystery Game Puzzles26%—
DTBench91.2%—
LMCA52.7%—
Surface Evolver Bench95%—
Epoch Capabilities Index157.45—
ForecastBench61.1—

Math Kimi K3 leads

Kimi K3: 74.2 (#16), Qwen1.5-32B: 33.0 (#207)

BenchmarkKimi K3Qwen1.5-32B
LMArena Math14911155
FrontierMath (Tiers 1-3)72.2%—
FrontierMath Tier 439%—
MathArena Final-Answer Competitions87.8%—
OTIS Mock AIME 2024-202597.2%—
ProofBench87%—

Knowledge Kimi K3 leads

Kimi K3: 63.2 (#21), Qwen1.5-32B: 13.5 (#296)

BenchmarkKimi K3Qwen1.5-32B
GPQA Diamond93.1%30.7%
LMArena Expert15211126
SimpleQA Verified50.6%—
MMLU—74.4%

Multimodal Not comparable

Kimi K3: 37.8 (#70), Qwen1.5-32B: —

BenchmarkKimi K3Qwen1.5-32B
Blueprint-Bench 229.5%—
Furniture Assembly34.2%—

Multilingual Kimi K3 leads

Kimi K3: 56.3 (#21), Qwen1.5-32B: 31.4 (#259)

BenchmarkKimi K3Qwen1.5-32B
LMArena Non-English14661106
LMArena Chinese15291177
LMArena French14911101
LMArena German14881058
LMArena Japanese14871027
LMArena Korean14581008
LMArena Russian14821073
LMArena Spanish14721089

Instruction Following Kimi K3 leads

Kimi K3: 77.7 (#14), Qwen1.5-32B: 57.7 (#265)

BenchmarkKimi K3Qwen1.5-32B
LMArena Instruction Following14831116

Long Context Kimi K3 leads

Kimi K3: 45.8 (#29), Qwen1.5-32B: 34.7 (#246)

BenchmarkKimi K3Qwen1.5-32B
LMArena Longer Query14941146

Writing & Preference Kimi K3 leads

Kimi K3: 76.6 (#4), Qwen1.5-32B: 34.2 (#271)

BenchmarkKimi K3Qwen1.5-32B
LMArena Text14761137
LMArena Creative Writing14541083
LMArena Multi-Turn14881140
EQ-Bench Creative Writing2082—
EQ-Bench 41339—

Frequently asked questions

Is Kimi K3 better than Qwen1.5-32B?

Kimi K3 is the stronger model overall, scoring 59.5 to 30.5 on the Noometry Index.

Is Kimi K3 or Qwen1.5-32B better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 31.7 in the Noometry coding category.

How many benchmarks do Kimi K3 and Qwen1.5-32B share?

18 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper