Resource detail

SWE-bench

A benchmark that tests model coding ability on real GitHub issues.

GlobalFreeOpen source

Visit official siteMore like this

At a glance

swe-bench

Pricing

Free

Access

No login

Platforms

Web

Chinese support

Last checked

2026-08-29

Popularity

78/100

Typical use

Coding model selectionAgent evaluation

Similar tools and resources

Selected by use case

Aider LLM Leaderboards

Aider's code-editing leaderboard, designed around real development tasks.

GlobalFreeOpen source+3

Updated 2026-08-29

Visit official site

LMArena

A public evaluation platform comparing LLM output quality through real-user voting.

GlobalFreeModel comparison+2

Updated 2026-08-29

Visit official site

Artificial Analysis

An independent model and API analysis site covering quality, speed, and price.

GlobalFreePerformance analysis+2

Updated 2026-08-29

Visit official site

LiveBench

A continuously refreshed, contamination-resistant benchmark with more reliable results.

GlobalFreeOpen source+3

Updated 2026-08-29

Visit official site

OpenCompass

Shanghai AI Lab's open evaluation suite and a respected Chinese-language leaderboard.

DomesticFreeOpen source+2

Updated 2026-08-29

Visit official site

SuperCLUE

A comprehensive Chinese LLM benchmark with monthly leaderboards.

DomesticFreeChinese evaluation+2

Updated 2026-08-29

Visit official site