# Multi-SWE Bench 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-multi-swe-bench

Every model the catalog carries a published Multi-SWE Bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Repository task completion |
| Tasks | Multi-language repo tasks |
| Difficulty | Professional software engineering |
| Published by | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |

A multi-language software-engineering benchmark that measures repository-level bug fixing and implementation across more than one programming ecosystem.

## Multi-SWE Bench ranking

1 model with a published Multi-SWE Bench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Repository task completion | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [MiniMax M2.7](https://modelchoice.dev/models/minimax-m2-7) | MiniMax | 52.7 | Observed 2026-11-21 · source benchlm:models |

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.
