Noometry

Model comparison

Claude 3 Haiku vs Kimi K3

Kimi K3 is the stronger model overall, scoring 59.5 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Kimi K3 Moonshot AI

59.5

Rank #15 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Haiku 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 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 97.2% for Kimi K3.
  • Kimi K3 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuKimi K3
ProviderAnthropicMoonshot AI
Noometry Index25.959.5
Released2024-03-072026-07-16
WeightsProprietaryOpen
Context window—1.05M
Max output—1.05M
Input $ / M tokens—$3
Output $ / M tokens—$15
Results tracked3753

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

Category by category

Coding Kimi K3 leads

Claude 3 Haiku: 26.4 (#325), Kimi K3: 61.0 (#10)

BenchmarkClaude 3 HaikuKimi K3
WeirdML9.8%82.6%
LMArena Coding11991508
DeepSWE—68.5%
FrontierCode—44.2%
LMArena WebDev—1654
FrontierSWE—25.9%
SciCode—59.5%
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—1,524
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

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

BenchmarkClaude 3 HaikuKimi 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 Haiku: 16.3 (#307), Kimi K3: 63.0 (#17)

BenchmarkClaude 3 HaikuKimi K3
LMArena Hard Prompts11741496
DTBench50.1%91.2%
LMCA8.8%52.7%
Epoch Capabilities Index118.35157.45
ForecastBench53.261.1
ARC-AGI-2—60.4%
SimpleBench—60.7%
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—93.6%
ARC-AGI-1—94.5%
CritPt—23.4%
Chess Puzzles—39%
Mystery Game Puzzles—26%
Surface Evolver Bench—95%
WinoGrande74.2%—

Math Kimi K3 leads

Claude 3 Haiku: 9.8 (#319), Kimi K3: 74.2 (#16)

BenchmarkClaude 3 HaikuKimi K3
OTIS Mock AIME 2024-20251.8%97.2%
LMArena Math11881491
FrontierMath (Tiers 1-3)—72.2%
FrontierMath Tier 4—39%
MathArena Final-Answer Competitions—87.8%
ProofBench—87%
MATH Level 514.9%—

Knowledge Kimi K3 leads

Claude 3 Haiku: 17.3 (#285), Kimi K3: 63.2 (#21)

BenchmarkClaude 3 HaikuKimi K3
GPQA Diamond36.3%93.1%
LMArena Expert11481521
SimpleQA Verified—50.6%
Confabulations34.2%—
MMLU73.8%—

Multimodal Kimi K3 leads

Claude 3 Haiku: 23.6 (#128), Kimi K3: 37.8 (#70)

BenchmarkClaude 3 HaikuKimi K3
LMArena Vision950—
Blueprint-Bench 2—29.5%
Furniture Assembly—34.2%
ScienceQA72%—

Multilingual Kimi K3 leads

Claude 3 Haiku: 36.0 (#243), Kimi K3: 56.3 (#21)

BenchmarkClaude 3 HaikuKimi K3
LMArena Non-English11781466
LMArena Chinese11551529
LMArena French11951491
LMArena German11741488
LMArena Japanese11021487
LMArena Korean11091458
LMArena Russian12041482
LMArena Spanish11661472

Instruction Following Kimi K3 leads

Claude 3 Haiku: 61.3 (#247), Kimi K3: 77.7 (#14)

BenchmarkClaude 3 HaikuKimi K3
LMArena Instruction Following11731483

Long Context Kimi K3 leads

Claude 3 Haiku: 36.1 (#237), Kimi K3: 45.8 (#29)

BenchmarkClaude 3 HaikuKimi K3
LMArena Longer Query11901494

Writing & Preference Kimi K3 leads

Claude 3 Haiku: 29.7 (#291), Kimi K3: 76.6 (#4)

BenchmarkClaude 3 HaikuKimi K3
LMArena Text11951476
LMArena Creative Writing11571454
EQ-Bench Creative Writing7172082
LMArena Multi-Turn11901488
EQ-Bench 4—1339

Frequently asked questions

Is Claude 3 Haiku better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 26.4 in the Noometry coding category.

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

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Kimi K3 has 53.

Related comparisons

Go deeper