Noometry

Model comparison

Claude 3 Sonnet vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Kimi K3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K3 leads 74.2 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 97.2% for Kimi K3.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetKimi K3
ProviderAnthropicMoonshot AI
Noometry Index29.059.5
Released2024-02-292026-07-16
WeightsProprietaryOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked3053

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

Category by category

Coding Kimi K3 leads

Claude 3 Sonnet: 29.6 (#302), Kimi K3: 61.0 (#10)

BenchmarkClaude 3 SonnetKimi K3
WeirdML10.2%82.6%
LMArena Coding12231508
DeepSWE—68.5%
FrontierCode—44.2%
LMArena WebDev—1654
FrontierSWE—25.9%
SciCode—59.5%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—1,524
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Kimi K3: 41.8 (#20)

BenchmarkClaude 3 SonnetKimi K3
APEX-Agents—50.6%
τ²-bench Banking—37.1%
PostTrainBench—32%
GBAEval—48.3%
GDP.pdf—19%
Vending-Bench 2—5,165

Reasoning Kimi K3 leads

Claude 3 Sonnet: 20.5 (#237), Kimi K3: 63.0 (#17)

BenchmarkClaude 3 SonnetKimi K3
LMArena Hard Prompts11971496
DTBench53.6%91.2%
Epoch Capabilities Index120.7157.45
ARC-AGI-2—60.4%
SimpleBench—60.7%
NYT Connections (extended)—93.6%
ARC-AGI-1—94.5%
CritPt—23.4%
Chess Puzzles—39%
Mystery Game Puzzles—26%
LMCA—52.7%
Surface Evolver Bench—95%
ForecastBench—61.1
WinoGrande75.1%—

Math Kimi K3 leads

Claude 3 Sonnet: 10.7 (#310), Kimi K3: 74.2 (#16)

BenchmarkClaude 3 SonnetKimi K3
OTIS Mock AIME 2024-20252.5%97.2%
LMArena Math12131491
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
ProofBench—87%
MATH Level 518.2%—

Knowledge Kimi K3 leads

Claude 3 Sonnet: 21.1 (#276), Kimi K3: 63.2 (#21)

BenchmarkClaude 3 SonnetKimi K3
GPQA Diamond40.6%93.1%
LMArena Expert11731521
SimpleQA Verified—50.6%
MMLU75.9%—

Multimodal Kimi K3 leads

Claude 3 Sonnet: 25.2 (#125), Kimi K3: 37.8 (#70)

BenchmarkClaude 3 SonnetKimi K3
LMArena Vision984—
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%

Multilingual Kimi K3 leads

Claude 3 Sonnet: 37.8 (#234), Kimi K3: 56.3 (#21)

BenchmarkClaude 3 SonnetKimi K3
LMArena Non-English12051466
LMArena Chinese11891529
LMArena French12291491
LMArena German12041488
LMArena Japanese11311487
LMArena Korean11281458
LMArena Russian12271482
LMArena Spanish12041472

Instruction Following Kimi K3 leads

Claude 3 Sonnet: 62.8 (#235), Kimi K3: 77.7 (#14)

BenchmarkClaude 3 SonnetKimi K3
LMArena Instruction Following11991483

Long Context Kimi K3 leads

Claude 3 Sonnet: 36.7 (#228), Kimi K3: 45.8 (#29)

BenchmarkClaude 3 SonnetKimi K3
LMArena Longer Query12111494

Writing & Preference Kimi K3 leads

Claude 3 Sonnet: 42.1 (#238), Kimi K3: 76.6 (#4)

BenchmarkClaude 3 SonnetKimi K3
LMArena Text12181476
LMArena Creative Writing11861454
LMArena Multi-Turn12271488
EQ-Bench Creative Writing—2082
EQ-Bench 4—1339

Frequently asked questions

Is Claude 3 Sonnet better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Kimi K3 share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper