Performance Scores

Overall

65
Rank #22 of 45 — Top 51%

SWE-bench

58
Rank #22 of 45 — Top 51%

LiveCodeBench

66
Rank #25 of 45 — Top 44%

HumanEval

84
Rank #24 of 45 — Top 47%

BigCodeBench

52
Rank #22 of 45 — Top 51%

Strengths & Weaknesses

Strengths

  • European data residency
  • Good value

Weaknesses

  • Smaller ecosystem

Compare with Similar-Priced Models

ModelOverall ScoreInput $/M
Mistral Large 2 65 $2.00
GPT-4o 75 $2.50
OpenAI o1-mini 70 $1.10
OpenAI o3-mini 80 $1.10
OpenAI o4-mini 72 $1.10