# FLTEval leaderboard

Coding benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/coding-flteval

Every model the catalog carries a published FLTEval value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Lean 4 repository task completion |
| Tasks | FLT project pull requests |
| Difficulty | Formal verification / proof engineering |
| Published by | [Leanstral: Open-Source foundation for trustworthy vibe-coding](https://mistral.ai/news/leanstral) |

A repository-level Lean 4 proof engineering benchmark that measures whether a model can complete formal proofs and correctly define new mathematical concepts inside realistic FLT project pull requests.

## FLTEval ranking

No model in the catalog has a published FLTEval score. The benchmark is defined by Leanstral: Open-Source foundation for trustworthy vibe-coding, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
