The open directory of AI agents, LLMs, MCP servers, workflows, and tools — search, compare, and track status across platforms.

Explore

Browse All AI Agents LLMs MCP Servers Tools & Frameworks

Account

Support

How It Works FAQ Report an Issue

Company

ATMEZ AI Solutions

Built with ❤️ for the AI community

All Agents LLMs MCP Servers Workflows Frameworks Tools Skills GenAI News

SWE-bench Verified Leaderboard | Genaihub

Back

Code & Software Engineering

Epoch live leaderboard

SWE-bench Verified

Human-validated software engineering issues from real-world Python repositories.

Published source(opens in a new tab)

Metric

Accuracy

Results shown

Publisher

Epoch AI live leaderboard

Snapshot

Fetched 2026-08-22T12:55:14.497Z

33 of 33 models

Claude 3.7 Sonnet

Claude Opus 4

Claude Opus 4.1

Claude Opus 4.5 (no thinking)

Claude Opus 4.6 (no thinking)

Claude Opus 4.7 (max)

Claude Sonnet 4.5 (no thinking)

Claude Sonnet 4.6 (no thinking)

DeepSeek v4 (max)

Gemini 2.5 Pro

Gemini 3 Flash Preview

Gemini 3 Pro Preview

Gemini 3.1 Pro Preview

Gemini 3.5 Flash (high)

GLM-5

GLM-5.1

GLM-5.2 (max)

GPT-4.1

GPT-4o (Nov 2024)

GPT-5 (high)

GPT-5 (medium)

GPT-5 mini (medium)

GPT-5.1 (high)

GPT-5.2 (high)

GPT-5.3 Codex (high)

GPT-5.4 (high)

GPT-5.5 (xhigh)

Kimi K2.5

Kimi K2.6

o3 (medium)

Qwen3.6 Max Preview (thinking)

Qwen3.6 Plus (thinking)

Qwen3.7 Max