Claude Sonnet 5
Anthropic
Won 1 of 1 blind comparison
Leaderboard
Real comparisons. Community choices.
Ranked by blind win rate, with at least five blind votes required across all tasks. Sighted votes are shown separately because model names can introduce brand bias. Only responses in recorded votes contribute to these figures.
Most recent vote included:
Across the site: 14 comparisons run · 1 vote recorded
Rankings come from blind head-to-head votes, before model identities are revealed.
Start a new comparisonProvisional
Early numbers from a small sample, not a ranking.
GPT-6 Luna
OpenAI
Won 0 of 1 blind comparison
Gemini 3.8 Flash
Won 0 of 1 blind comparison
Not enough data yet
No blind comparisons recorded for these models yet.
Claude Fable 5.1
Anthropic
—
Claude Opus 5.5
Anthropic
—
GLM 5.2
Z.ai
—
GPT-6 Astra
OpenAI
—
GPT-6 Sol
OpenAI
—