FormalTCS - Theorem Proving: leaderboard
Metric: Pass@8 (%; at least one of 8 sampled Lean 4 proofs of the human-annotated formal theorem accepted by the Lean compiler with warnings as errors and an axiom whitelist; 143 instances from theoretical computer science papers accepted at STOC, FOCS, SODA, COLT and similar venues in 2025-2026, each stage given the human-annotated input; each model runs in its own vendor harness). Source: arxiv.org. Saturation forecast: Around August 2028. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (Claude Code) | 28.7 |
| 2 | GPT-5.6 Sol (Codex) | 26.6 |
| 3 | Claude Sonnet 5 (Claude Code) | 23.8 |
| 4 | Claude Haiku 4.5 (Claude Code) | 7.7 |
Interactive version: theaggregate.ai/benchmark?slug=formaltcs-theorem-proving · How It Works · Data refreshed daily, snapshot 2026-09-26.