CtrlK

GenAiHub

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

10,000+AI Tools

50+Categories

DailyUpdates

ByATMEZ AI Solutions

Explore

Browse All AI Agents LLMs MCP Servers Tools & Frameworks

Account

Sign In Create Account Submit an Agent Saved Agents

Support

How It Works FAQ Report an Issue

Company

© 2026ATMEZ AI Solutions·All rights reserved.

Built with ❤️ for the AI community|Privacy Terms

Explore Agents LLMs MCP Servers Workflows Frameworks Tools Skills News

MCP Atlas Leaderboard | GenAiHub

Task Planning & Knowledge Search

All 1,000 tasks

MCP Atlas

Real-world multi-step tool-use evaluation through the Model Context Protocol.

Published source(opens in a new tab)

Metric

Pass rate

Results shown

35

Publisher

Scale Labs leaderboard

Snapshot

Fetched 2026-09-17T23:25:26.942Z

35 of 35 models

Claude Fable 5

claude-haiku-4-5

claude-opus-4-5 (high)

claude-opus-4-6 (max)

claude-opus-4-7 (max)

claude-opus-4-8 (max)

claude-opus-5 (xhigh)

claude-sonnet-4-5 (thinking)

claude-sonnet-4-6

Fa

Fable 5.1

Gemini 3.5 Flash (high)

gemini-3-flash-preview

gemini-3-pro-preview

gemini-3.1-flash-lite (high)

gemini-3.1-pro-preview (high)

GLM 5.3

glm-4p7

glm-5p1

glm-5p2

gpt-5.1 (high)

gpt-5.2 (xhigh)

gpt-5.4 (xhigh)

gpt-5.4-mini (xhigh)

gpt-5.5 (xhigh)

gpt-5.6 (sol)

In

Inkling (xHigh)

In

Inkling-small

kimi-k2p5

kimi-k3 (max)

Muse Spark

Muse Spark 1.1

Ne

Nemotron 3 Ultra

Ne

Nemotron 3 Ultra (xHigh)

o3-pro

Qwen3.8-2.4T-A95B (xHigh)

35 of 35 models

Higher is better

25

50

75

100

88

Muse Spark 1.1

87

Fa

Fable 5.1

86

claude-opus-5 (xhigh)

85

Qwen3.8-2.4T-A95B (xHigh)

84

GLM 5.3

84

Gemini 3.5 Flash (high)

83

Claude Fable 5

82

kimi-k3 (max)

82

claude-opus-4-8 (max)

82

Muse Spark

82

gpt-5.6 (sol)

79

In

Inkling-small

79

claude-opus-4-7 (max)

78

gemini-3.1-pro-preview (high)

78

glm-5p2

77

claude-opus-4-6 (max)

76

In

Inkling (xHigh)

76

glm-5p1

75

gpt-5.5 (xhigh)

71

gpt-5.4 (xhigh)

70

gemini-3-pro-preview

70

claude-opus-4-5 (high)

70

claude-sonnet-4-6

68

gpt-5.2 (xhigh)

64

kimi-k2p5

63

Ne

Nemotron 3 Ultra (xHigh)

63

Ne

Nemotron 3 Ultra

62

gemini-3-flash-preview

60

claude-sonnet-4-5 (thinking)

58

glm-4p7

57

gemini-3.1-flash-lite (high)

57

gpt-5.4-mini (xhigh)

50

gpt-5.1 (high)

45

o3-pro

40

claude-haiku-4-5

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.