Terminal-Bench 3.0 Leaderboard

All Agents LLMs MCP Servers Workflows Frameworks Tools Skills GenAI News

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

Terminal-Bench 3.0 Leaderboard | Genaihub

Back

Code & Software Engineering

Terminal-Bench 3.0

The official leaderboard for Terminal-Bench 3.0.

Published source(opens in a new tab)

Metric

Accuracy

Results shown

Publisher

FrontierBench (Terminal-Bench) public leaderboard

Snapshot

Fetched 2026-09-03T12:26:35.083Z

12 of 12 models

Fable 5

GLM 5.2

GLM 5.3

GPT-5.6 Luna

GPT-5.6 Sol

GPT-5.6 Terra

Grok 4.5

Grok 4.6

Opus 4.8

Opus 5

Sonnet 5

SWE-1.7 Lightning

12 of 12 models

Higher is better

100

42.7

Opus 5

34.6

GPT-5.6 Sol

34.0

Fable 5

32.4

GLM 5.3

26.5

Grok 4.6

21.1

Opus 4.8

20.8

GPT-5.6 Terra

18.6

SWE-1.7 Lightning

15.7

Grok 4.5

14.6

Sonnet 5

14.3

GPT-5.6 Luna

4.6

GLM 5.2

List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.

Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.