Noometry

Model comparison

Claude 3 Sonnet vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 28.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3 Sonnet Anthropic

28.8

Rank #311 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.4

Rank #63 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 10.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 83.1% for Kimi K2 Thinking Turbo.
  • Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetKimi K2 Thinking Turbo
ProviderAnthropicMoonshot AI
Noometry Index28.845.4
Released2024-02-292025-11-06
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3021

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

Category by category

Coding Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 29.2 (#296), Kimi K2 Thinking Turbo: 38.1 (#166)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Coding12231454
LMArena WebDev—1322
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 19.7 (#232), Kimi K2 Thinking Turbo: 31.4 (#72)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Hard Prompts11971428
Chess Puzzles—20%
DTBench53.6%—
Epoch Capabilities Index120.69—
WinoGrande75.1%—

Math Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 10.0 (#305), Kimi K2 Thinking Turbo: 45.5 (#62)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
OTIS Mock AIME 2024-20252.5%83.1%
LMArena Math12131429
MATH Level 518.2%—

Knowledge Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 21.1 (#271), Kimi K2 Thinking Turbo: 50.9 (#64)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
GPQA Diamond40.6%84.2%
LMArena Expert11731439
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 24.7 (#120), Kimi K2 Thinking Turbo: —

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Vision984—

Multilingual Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 38.0 (#229), Kimi K2 Thinking Turbo: 51.6 (#104)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Non-English12051398
LMArena Chinese11881457
LMArena French12281425
LMArena German12041390
LMArena Japanese11311356
LMArena Korean11281329
LMArena Russian12271390
LMArena Spanish12041407

Instruction Following Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 63.1 (#230), Kimi K2 Thinking Turbo: 74.2 (#103)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Instruction Following12001403

Long Context Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 36.7 (#223), Kimi K2 Thinking Turbo: 43.2 (#99)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Longer Query12111415

Writing & Preference Kimi K2 Thinking Turbo leads

Claude 3 Sonnet: 42.3 (#233), Kimi K2 Thinking Turbo: 60.2 (#99)

BenchmarkClaude 3 SonnetKimi K2 Thinking Turbo
LMArena Text12181415
LMArena Creative Writing11861373
LMArena Multi-Turn12271414

Frequently asked questions

Is Claude 3 Sonnet better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 28.8 on the Noometry Index.

Is Claude 3 Sonnet or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 29.2 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Kimi K2 Thinking Turbo share?

19 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper