benchlm.ai

Claude 3 Haiku vs Kimi K2.5 (Reasoning)

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Kimi K2.5 (Reasoning) wins overall with a score of 71 vs 46 (25 point difference).Kimi K2.5 (Reasoning) wins 4 out of 4 categories.

Claude 3 Haiku

CreatorAnthropic
TypeProprietary
Context200K
Score46

Kimi K2.5 (Reasoning)

CreatorMoonshot AI
TypeOpen Weight
Context128K
Score71

Knowledge

Kimi K2.5 (Reasoning)

Claude 3 Haiku

54.5

Kimi K2.5 (Reasoning)

89

56
MMLU
92
56
GPQA
90
54
SuperGPQA
88
52
OpenBookQA
86

Coding

Kimi K2.5 (Reasoning)

Claude 3 Haiku

48

Kimi K2.5 (Reasoning)

84

48
HumanEval
84

Mathematics

Kimi K2.5 (Reasoning)

Claude 3 Haiku

55

Kimi K2.5 (Reasoning)

93

56
AIME 2023
94
58
AIME 2024
96
57
AIME 2025
95
52
HMMT Feb 2023
90
54
HMMT Feb 2024
92
53
HMMT Feb 2025
91
55
BRUMO 2025
93

Reasoning

Kimi K2.5 (Reasoning)

Claude 3 Haiku

53

Kimi K2.5 (Reasoning)

87

54
SimpleQA
88
52
MuSR
86

Frequently Asked Questions

Which is better, Claude 3 Haiku or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) scores higher overall with 71 vs 46, a difference of 25 points across all benchmarks.

Which is better for knowledge tasks, Claude 3 Haiku or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in knowledge tasks with an average score of 89 vs 54.5.

Which is better for coding, Claude 3 Haiku or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in coding with an average score of 84 vs 48.

Which is better for math, Claude 3 Haiku or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in math with an average score of 93 vs 55.

Which is better for reasoning, Claude 3 Haiku or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in reasoning with an average score of 87 vs 53.

Related Comparisons

Claude 3 Haiku vs GPT-5.4Claude 3 Haiku vs Gemini 3.1 ProClaude 3 Haiku vs Claude Opus 4.6Claude 3 Haiku vs GPT-5.3 CodexClaude 3 Haiku vs Grok 4.1Claude 3 Haiku vs GPT-5.2