Noometry

Model comparison

Kimi K3 vs Qwen3.8 Max

Kimi K3 is the stronger model overall, scoring 59.5 to 56.8 on the Noometry Index. Qwen3.8 Max costs 2.0× 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

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Qwen3.8 Max in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K3 leads 76.6 to 67.1.
  • The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 58% for Qwen3.8 Max.
  • Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Kimi K3.
  • Kimi K3 accepts more context: 1.05M tokens versus 1M.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Kimi K3Qwen3.8 Max
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index59.556.8
Released2026-07-162026-08-02
WeightsOpenProprietary
Context window1.05M1M
Max output1.05M131K
Input $ / M tokens$3$2
Output $ / M tokens$15$6
Results tracked5339

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

Category by category

Coding Kimi K3 leads

Kimi K3: 61.0 (#10), Qwen3.8 Max: 53.5 (#29)

BenchmarkKimi K3Qwen3.8 Max
DeepSWE68.5%57.5%
LMArena WebDev16541674
FrontierSWE25.9%17.8%
SciCode59.5%53.2%
LMArena Coding15081502
FrontierCode44.2%—
WeirdML82.6%—
ALE-Bench1,524—

Agentic & Tool Use Qwen3.8 Max leads

Kimi K3: 41.8 (#20), Qwen3.8 Max: 45.4 (#14)

BenchmarkKimi K3Qwen3.8 Max
APEX-Agents50.6%63.3%
τ²-bench Banking37.1%55.1%
GDP.pdf19%23.2%
PostTrainBench32%—
GBAEval48.3%—
Vending-Bench 25,165—

Reasoning Kimi K3 leads

Kimi K3: 63.0 (#17), Qwen3.8 Max: 54.4 (#26)

BenchmarkKimi K3Qwen3.8 Max
NYT Connections (extended)93.6%88.3%
CritPt23.4%20%
Chess Puzzles39%40%
LMArena Hard Prompts14961496
Mystery Game Puzzles26%38%
DTBench91.2%92%
LMCA52.7%46.2%
Epoch Capabilities Index157.45156.41
ARC-AGI-260.4%—
SimpleBench60.7%—
ARC-AGI-194.5%—
Surface Evolver Bench95%—
ForecastBench61.1—

Math Too close to call

Kimi K3: 74.2 (#16), Qwen3.8 Max: 73.2 (#20)

BenchmarkKimi K3Qwen3.8 Max
FrontierMath (Tiers 1-3)72.2%74.7%
FrontierMath Tier 439%46.3%
OTIS Mock AIME 2024-202597.2%100%
ProofBench87%58%
LMArena Math14911499
MathArena Final-Answer Competitions87.8%—

Knowledge Kimi K3 leads

Kimi K3: 63.2 (#21), Qwen3.8 Max: 61.7 (#27)

BenchmarkKimi K3Qwen3.8 Max
GPQA Diamond93.1%92.7%
SimpleQA Verified50.6%47.3%
LMArena Expert15211507

Multimodal Too close to call

Kimi K3: 37.8 (#70), Qwen3.8 Max: 37.2 (#75)

BenchmarkKimi K3Qwen3.8 Max
Furniture Assembly34.2%20%
LMArena Vision—1314
Blueprint-Bench 229.5%—

Multilingual Too close to call

Kimi K3: 56.3 (#21), Qwen3.8 Max: 56.7 (#18)

BenchmarkKimi K3Qwen3.8 Max
LMArena Non-English14661472
LMArena Chinese15291538
LMArena French14911503
LMArena German14881483
LMArena Japanese14871467
LMArena Korean14581461
LMArena Russian14821481
LMArena Spanish14721492

Instruction Following Too close to call

Kimi K3: 77.7 (#14), Qwen3.8 Max: 77.6 (#17)

BenchmarkKimi K3Qwen3.8 Max
LMArena Instruction Following14831479

Long Context Too close to call

Kimi K3: 45.8 (#29), Qwen3.8 Max: 45.6 (#31)

BenchmarkKimi K3Qwen3.8 Max
LMArena Longer Query14941489

Writing & Preference Kimi K3 leads

Kimi K3: 76.6 (#4), Qwen3.8 Max: 67.1 (#30)

BenchmarkKimi K3Qwen3.8 Max
LMArena Text14761483
LMArena Creative Writing14541479
LMArena Multi-Turn14881489
EQ-Bench Creative Writing2082—
EQ-Bench 41339—

Frequently asked questions

Is Kimi K3 better than Qwen3.8 Max?

Kimi K3 is the stronger model overall, scoring 59.5 to 56.8 on the Noometry Index. Qwen3.8 Max costs 2.0× 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 Qwen3.8 Max?

Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Kimi K3 lists at $3 and $15.

Is Kimi K3 or Qwen3.8 Max better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 53.5 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 Qwen3.8 Max share?

38 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper