Noometry

Model comparison

Kimi K2 Thinking Turbo vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.8 on the Noometry Index.

Last verified . 21 shared benchmarks.

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 47.4.
  • The biggest single-benchmark swing is Chess Puzzles: 20% for Kimi K2 Thinking Turbo and 40% for Qwen3.8 Max.
  • Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

Side by side

Kimi K2 Thinking TurboQwen3.8 Max
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index45.856.8
Released2025-11-062026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked2139

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

Category by category

Coding Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 38.4 (#178), Qwen3.8 Max: 53.5 (#29)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena WebDev13221674
LMArena Coding14541502
DeepSWE—57.5%
FrontierSWE—17.8%
SciCode—53.2%

Agentic & Tool Use Not comparable

Kimi K2 Thinking Turbo: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 32.5 (#75), Qwen3.8 Max: 54.4 (#26)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
Chess Puzzles20%40%
LMArena Hard Prompts14281496
NYT Connections (extended)—88.3%
CritPt—20%
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
Epoch Capabilities Index—156.41

Math Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 47.4 (#68), Qwen3.8 Max: 73.2 (#20)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
OTIS Mock AIME 2024-202583.1%100%
LMArena Math14291499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
ProofBench—58%

Knowledge Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 50.9 (#69), Qwen3.8 Max: 61.7 (#27)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
GPQA Diamond84.2%92.7%
LMArena Expert14391507
SimpleQA Verified—47.3%

Multimodal Not comparable

Kimi K2 Thinking Turbo: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 51.4 (#109), Qwen3.8 Max: 56.7 (#18)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena Non-English13981472
LMArena Chinese14561538
LMArena French14251503
LMArena German13901483
LMArena Japanese13571467
LMArena Korean13301461
LMArena Russian13911481
LMArena Spanish14061492

Instruction Following Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 74.0 (#109), Qwen3.8 Max: 77.6 (#17)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena Instruction Following14031479

Long Context Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 43.2 (#102), Qwen3.8 Max: 45.6 (#31)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena Longer Query14151489

Writing & Preference Qwen3.8 Max leads

Kimi K2 Thinking Turbo: 60.0 (#104), Qwen3.8 Max: 67.1 (#30)

BenchmarkKimi K2 Thinking TurboQwen3.8 Max
LMArena Text14151483
LMArena Creative Writing13741479
LMArena Multi-Turn14141489

Frequently asked questions

Is Kimi K2 Thinking Turbo better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 45.8 on the Noometry Index.

Is Kimi K2 Thinking Turbo or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.4 in the Noometry coding category.

How many benchmarks do Kimi K2 Thinking Turbo and Qwen3.8 Max share?

21 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper