Performance Scores

Overall

48
Rank #39 of 45 — Top 13%

SWE-bench

40
Rank #39 of 45 — Top 13%

LiveCodeBench

50
Rank #39 of 45 — Top 13%

HumanEval

70
Rank #39 of 45 — Top 13%

BigCodeBench

32
Rank #39 of 45 — Top 13%

Strengths & Weaknesses

Strengths

  • Open weight
  • Self-hostable

Weaknesses

  • Basic coding ability

Compare with Similar-Priced Models

ModelOverall ScoreInput $/M
Mistral Nemo 48 $0.150
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