ITPEval - Babel-formal Proofs: leaderboard

Metric: Pass@1 (%; share of the 192 directed Babel-formal (tier A) proof pairs whose single translated proof verifies; zero-shot direct translation at temperature 0: given a source file in Lean 4, Isabelle, Rocq or HOL Light and a target prover, emit raw target code, which must verify under the target prover). Source: arxiv.org. Saturation forecast: Around August 2027. 5 models tracked.

Top models

#ModelScore
1GPT-5.529.69
2Gemini 3.1 Pro (Preview)18.23
3Claude Sonnet 4.65.73
4DeepSeek V4 Pro4.69
5Qwen 3 235B A22B1.56

Interactive version: theaggregate.ai/benchmark?slug=itpeval-babel-formal-proofs · How It Works · Data refreshed daily, snapshot 2026-09-29.