Noometry

Model comparison

Kimi K3 vs MiniMax-M3

Kimi K3 is the stronger model overall, scoring 59.5 to 43.8 on the Noometry Index. MiniMax-M3 costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

Last verified . 38 shared benchmarks.

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Kimi K3 scores higher in 9 categories and MiniMax-M3 in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K3 leads 74.2 to 40.0.
  • The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 18% for MiniMax-M3.
  • MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Kimi K3.
  • Kimi K3 accepts more context: 1.05M tokens versus 1M.

Side by side

Kimi K3MiniMax-M3
ProviderMoonshot AIMiniMax
Noometry Index59.543.8
Released2026-07-162026-06-01
WeightsOpenOpen
Context window1.05M1M
Max output1.05M512K
Input $ / M tokens$3$0.30
Output $ / M tokens$15$1.20
Results tracked5341

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

Category by category

Coding Kimi K3 leads

Kimi K3: 61.0 (#10), MiniMax-M3: 41.8 (#118)

BenchmarkKimi K3MiniMax-M3
FrontierCode44.2%14.7%
LMArena WebDev16541482
SciCode59.5%47.1%
LMArena Coding15081469
ALE-Bench1,524640.02
DeepSWE68.5%—
FrontierSWE25.9%—
WeirdML82.6%—

Agentic & Tool Use Kimi K3 leads

Kimi K3: 41.8 (#20), MiniMax-M3: 22.6 (#130)

BenchmarkKimi K3MiniMax-M3
APEX-Agents50.6%37.7%
GBAEval48.3%0.9%
Vending-Bench 25,1652,158
OSWorld 2.0—4.6%
τ²-bench Banking37.1%—
PostTrainBench32%—
GDP.pdf19%—

Reasoning Kimi K3 leads

Kimi K3: 63.0 (#17), MiniMax-M3: 30.1 (#87)

BenchmarkKimi K3MiniMax-M3
SimpleBench60.7%45.8%
NYT Connections (extended)93.6%65.1%
CritPt23.4%3.7%
Chess Puzzles39%14%
LMArena Hard Prompts14961447
Mystery Game Puzzles26%8%
DTBench91.2%78.9%
LMCA52.7%33.7%
Surface Evolver Bench95%55%
Epoch Capabilities Index157.45146.95
ForecastBench61.161.4
ARC-AGI-260.4%—
ARC-AGI-194.5%—

Math Kimi K3 leads

Kimi K3: 74.2 (#16), MiniMax-M3: 40.0 (#95)

BenchmarkKimi K3MiniMax-M3
OTIS Mock AIME 2024-202597.2%71.1%
ProofBench87%18%
LMArena Math14911429
FrontierMath (Tiers 1-3)72.2%—
FrontierMath Tier 439%—
MathArena Final-Answer Competitions87.8%—

Knowledge Kimi K3 leads

Kimi K3: 63.2 (#21), MiniMax-M3: 58.4 (#35)

BenchmarkKimi K3MiniMax-M3
GPQA Diamond93.1%90.9%
LMArena Expert15211461
SimpleQA Verified50.6%—

Multimodal MiniMax-M3 leads

Kimi K3: 37.8 (#70), MiniMax-M3: 40.2 (#51)

BenchmarkKimi K3MiniMax-M3
LMArena Vision—1253
Blueprint-Bench 229.5%—
Furniture Assembly34.2%—
LMArena Document—1435

Multilingual Kimi K3 leads

Kimi K3: 56.3 (#21), MiniMax-M3: 53.0 (#75)

BenchmarkKimi K3MiniMax-M3
LMArena Non-English14661420
LMArena Chinese15291463
LMArena French14911447
LMArena German14881426
LMArena Japanese14871381
LMArena Korean14581372
LMArena Russian14821428
LMArena Spanish14721432

Instruction Following Kimi K3 leads

Kimi K3: 77.7 (#14), MiniMax-M3: 75.5 (#62)

BenchmarkKimi K3MiniMax-M3
LMArena Instruction Following14831433

Long Context Kimi K3 leads

Kimi K3: 45.8 (#29), MiniMax-M3: 44.2 (#72)

BenchmarkKimi K3MiniMax-M3
LMArena Longer Query14941445

Writing & Preference Kimi K3 leads

Kimi K3: 76.6 (#4), MiniMax-M3: 62.1 (#83)

BenchmarkKimi K3MiniMax-M3
LMArena Text14761433
LMArena Creative Writing14541404
EQ-Bench 413391150
LMArena Multi-Turn14881442
EQ-Bench Creative Writing2082—

Frequently asked questions

Is Kimi K3 better than MiniMax-M3?

Kimi K3 is the stronger model overall, scoring 59.5 to 43.8 on the Noometry Index. MiniMax-M3 costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

Which is cheaper, Kimi K3 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K3 lists at $3 and $15.

Is Kimi K3 or MiniMax-M3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

Kimi K3 does, with 1.05M tokens against 1M.

How many benchmarks do Kimi K3 and MiniMax-M3 share?

38 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper