Coding

Weighted toward coding capability and tool use, for developer-focused use cases.

Coding ranking, formula version 1.0.0, calculated 2026-09-21
RankModelScoreConfidenceEvidenceCodingTool UseReasoning
1Claude Sonnet · Anthropic87.484%2,25186100100
2GPT Frontier · OpenAI86.184%2,2511008887
3Gemini Pro · Google DeepMind72.884%2,251648073
4Llama Open · Meta AI8.072%446000

Scores are based on sample data for demonstration purposes.

Formula version 1.0.0 · weights v1.0.0 · calculated 2026-09-21. See the methodology page for how scores, confidence and evidence are combined.