ITPEval - Formalizing 100 Theorems Statements: leaderboard
ITPEval measures formal translation between interactive theorem provers: given a source file in Lean 4, Isabelle, Rocq or HOL Light, the model emits the same content in a target prover and a unified verifier checks it there. This board covers statement translation on Formalizing 100 Theorems, which needs real library APIs and prover-specific conventions. The score is the share of directed source-to-target pairs that verify from a single greedy attempt.
Metric: Pass@1 (%; share of the 696 directed Formalizing 100 Theorems (tier B, ecosystem) statement pairs whose single translated statement 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 December 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 15.23 | #49 |
| 2 | Gemini 3.1 Pro (Preview) | 13.94 | #94 |
| 3 | DeepSeek V4 Pro | 6.61 | #188 |
| 4 | Claude Sonnet 4.6 | 4.6 | #161 |
| 5 | Qwen 3 235B A22B | 1.44 | #623 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=itpeval-formalizing-100-theorems-statements · How It Works · Data refreshed daily, snapshot 2026-11-13.