Noometry

Model comparison

Claude 3 Haiku vs Kimi K2.5 Instant

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 25.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Kimi K2.5 Instant Moonshot AI

43.6

Rank #89 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Kimi K2.5 Instant in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Kimi K2.5 Instant leads 60.6 to 29.7.
  • Kimi K2.5 Instant has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuKimi K2.5 Instant
ProviderAnthropicMoonshot AI
Noometry Index25.943.6
Released2024-03-07—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3718

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

Category by category

Coding Kimi K2.5 Instant leads

Claude 3 Haiku: 26.4 (#325), Kimi K2.5 Instant: 42.6 (#97)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Coding11991484
LMArena WebDev—1404
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Kimi K2.5 Instant leads

Claude 3 Haiku: 16.3 (#307), Kimi K2.5 Instant: 29.7 (#90)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Hard Prompts11741443
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Kimi K2.5 Instant leads

Claude 3 Haiku: 9.8 (#319), Kimi K2.5 Instant: 39.4 (#105)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Math11881442
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Kimi K2.5 Instant leads

Claude 3 Haiku: 17.3 (#285), Kimi K2.5 Instant: 40.2 (#123)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Expert11481440
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Kimi K2.5 Instant leads

Claude 3 Haiku: 23.6 (#128), Kimi K2.5 Instant: 40.2 (#50)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Vision9501254
ScienceQA72%—

Multilingual Kimi K2.5 Instant leads

Claude 3 Haiku: 36.0 (#243), Kimi K2.5 Instant: 52.0 (#94)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Non-English11781406
LMArena Chinese11551449
LMArena French11951403
LMArena German11741413
LMArena Korean11091378
LMArena Russian12041404
LMArena Spanish11661447
LMArena Japanese1102—

Instruction Following Kimi K2.5 Instant leads

Claude 3 Haiku: 61.3 (#247), Kimi K2.5 Instant: 75.3 (#65)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Instruction Following11731430

Long Context Kimi K2.5 Instant leads

Claude 3 Haiku: 36.1 (#237), Kimi K2.5 Instant: 43.9 (#83)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Longer Query11901435

Writing & Preference Kimi K2.5 Instant leads

Claude 3 Haiku: 29.7 (#291), Kimi K2.5 Instant: 60.6 (#95)

BenchmarkClaude 3 HaikuKimi K2.5 Instant
LMArena Text11951420
LMArena Creative Writing11571381
LMArena Multi-Turn11901427
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Kimi K2.5 Instant?

Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Kimi K2.5 Instant better for coding?

Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Kimi K2.5 Instant share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Kimi K2.5 Instant has 18.

Related comparisons

Go deeper