Performance Scores

Overall

70
Rank #14 of 45 — Top 69%

SWE-bench

64
Rank #14 of 45 — Top 69%

LiveCodeBench

74
Rank #12 of 45 — Top 73%

HumanEval

88
Rank #14 of 45 — Top 69%

BigCodeBench

56
Rank #12 of 45 — Top 73%

Strengths & Weaknesses

Strengths

  • Good value
  • Strong coding

Weaknesses

  • Less capable than full Sonnet 4

Compare with Similar-Priced Models

ModelOverall ScoreInput $/M
Claude Sonnet 4 Lite 70 $1.00
Claude 3.5 Haiku 52 $0.800
Claude 3 Haiku 45 $0.250
GPT-4o mini 58 $0.150
GPT-3.5 Turbo 40 $0.500
OpenAI o1-mini 70 $1.10