benchlm.ai

Claude Haiku 4.5 vs Llama 3 70B

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

Quick Verdict

Claude Haiku 4.5 wins overall with a score of 57 vs 48 (9 point difference).Claude Haiku 4.5 wins 4 out of 4 categories.

Claude Haiku 4.5

CreatorAnthropic
TypeProprietary
Context200K
Score57

Llama 3 70B

CreatorMeta
TypeOpen Weight
Context128K
Score48

Knowledge

Claude Haiku 4.5

Claude Haiku 4.5

65.8

Llama 3 70B

56.5

68
MMLU
58
67
GPQA
58
65
SuperGPQA
56
63
OpenBookQA
54

Coding

Claude Haiku 4.5

Claude Haiku 4.5

60

Llama 3 70B

50

60
HumanEval
50

Mathematics

Claude Haiku 4.5

Claude Haiku 4.5

67

Llama 3 70B

57

68
AIME 2023
58
70
AIME 2024
60
69
AIME 2025
59
64
HMMT Feb 2023
54
66
HMMT Feb 2024
56
65
HMMT Feb 2025
55
67
BRUMO 2025
57

Reasoning

Claude Haiku 4.5

Claude Haiku 4.5

64

Llama 3 70B

55

65
SimpleQA
56
63
MuSR
54

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or Llama 3 70B?

Claude Haiku 4.5 scores higher overall with 57 vs 48, a difference of 9 points across all benchmarks.

Which is better for knowledge tasks, Claude Haiku 4.5 or Llama 3 70B?

Claude Haiku 4.5 leads in knowledge tasks with an average score of 65.8 vs 56.5.

Which is better for coding, Claude Haiku 4.5 or Llama 3 70B?

Claude Haiku 4.5 leads in coding with an average score of 60 vs 50.

Which is better for math, Claude Haiku 4.5 or Llama 3 70B?

Claude Haiku 4.5 leads in math with an average score of 67 vs 57.

Which is better for reasoning, Claude Haiku 4.5 or Llama 3 70B?

Claude Haiku 4.5 leads in reasoning with an average score of 64 vs 55.

Related Comparisons

Claude Haiku 4.5 vs GPT-5.4Claude Haiku 4.5 vs Gemini 3.1 ProClaude Haiku 4.5 vs Claude Opus 4.6Claude Haiku 4.5 vs GPT-5.3 CodexClaude Haiku 4.5 vs Grok 4.1Claude Haiku 4.5 vs GPT-5.2