Claude Opus 5 Tops ProgramBench, Doubling Fully Resolved Tests
jyangballin · x · 2026-08-13
Claude Opus 5 (xhigh) takes the #1 spot on the ProgramBench benchmark, which tasks AI with rebuilding whole programs like sqlite and ffmpeg from scratch.
Every metric hit a record high: fully resolved tests (100% pass rate) jumped from 2 to 9 out of 200; near-perfect scores (>95% pass rate) increased from 33 to 74; and the average test pass rate rose from 70.9% to 74.7%.
Related event: Claude Opus 5 Tops ProgramBench Coding Benchmark(7 posts)→
More from Models
- Unverified claim: Apple and Meta's 816B-parameter Muse Spark Open runs on two Mac Studios — TansuYegen · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- Every AI picks 7: Anthropic engineer's rule for escaping model taste convergence — rubenhassid · 2026-10-16
- Brain teaser: strip all attention, MLP and embedding matrices from a Llama 3 — how many trainable params remain? — Sauers_ · 2026-10-16
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16
- One flagged seat froze an entire Claude team org — founders share backup plans — RexDouglass · 2026-10-16