FrontierCode Diamond leaderboard
FrontierCode Diamond
1 models tested · Updated 2026-06-09 · Verified sources only
Claude Fable 5 leads at 29.3%
1
Claude Fable 5
Anthropic · Blog/Anthropic · 2026-06-09
Highest among frontier models at xhigh effort. GPT-5.5 scores 5.7%.
29.3%
benchmark.space canonical public ledger of AI capability