Noometry

Model comparison

Claude 3.5 Haiku vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3.5 Haiku 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 47.4 to 14.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku 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 3.5 HaikuKimi K2 Thinking Turbo
ProviderAnthropicMoonshot AI
Noometry Index29.245.8
Released2024-10-222025-11-06
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4921

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

Category by category

Coding Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 32.9 (#265), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Coding12861454
Aider Polyglot28%—
LMArena WebDev—1322
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Kimi K2 Thinking Turbo: —

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
BALROG19.3%—

Reasoning Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 17.7 (#290), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Hard Prompts12511428
CritPt0%—
Chess Puzzles—20%
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 14.7 (#300), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
OTIS Mock AIME 2024-20254.3%83.1%
LMArena Math12441429
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 18.7 (#281), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
GPQA Diamond38.1%84.2%
LMArena Expert12081439
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Kimi K2 Thinking Turbo: —

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Vision1092—
GeoBench34%—

Multilingual Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 40.0 (#218), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Non-English12381398
LMArena Chinese12291456
LMArena French12641425
LMArena German12371390
LMArena Japanese11751357
LMArena Korean11731330
LMArena Russian12531391
LMArena Spanish12611406

Instruction Following Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 62.9 (#234), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Instruction Following12411403
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 38.3 (#200), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Longer Query12611415

Writing & Preference Kimi K2 Thinking Turbo leads

Claude 3.5 Haiku: 42.7 (#234), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkClaude 3.5 HaikuKimi K2 Thinking Turbo
LMArena Text12551415
LMArena Creative Writing12331374
LMArena Multi-Turn12651414
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Kimi K2 Thinking Turbo share?

19 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper