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
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 29.69 |
| 2 | Gemini 3.1 Pro (Preview) | 18.23 |
| 3 | Claude Sonnet 4.6 | 5.73 |
| 4 | DeepSeek V4 Pro | 4.69 |
| 5 | Qwen 3 235B A22B | 1.56 |
Interactive version: theaggregate.ai/benchmark?slug=itpeval-babel-formal-proofs · How It Works · Data refreshed daily, snapshot 2026-09-29.