Skip to main content

GAIA Leaderboard — AI Model Benchmarks — MCP App Store | MCP App Store

AI Model Leaderboard

Compare AI models across agentic, reasoning, coding, and tool-use benchmarks.

Agentic

GAIA WebArena WebArena-Infinity τ³-bench TheAgentCompany VisualWebArena HAL METR Time Horizon BrowseComp BrowseComp (w/ Context Manage)MCP-Atlas (Public Set)Vending Bench 2

Agentic Reasoning Coding Tool Use Computer Use

Benchmarks

agentic

reasoning

coding

tool-use

computer-use

GAIA

466 human-curated multi-step tasks requiring web browsing, tool use, and file parsing. The gold standard for real-world agent capability.

Agentic49 models · % accuracy

MCP App Store

The AI ecosystem directory — MCP Apps, Agent Skills, and daily news.

Directory

MCP Apps & Servers Agent Skills AI News AI Models What are MCP Apps?

Resources

Documentation Specification GitHub

Account

Sign in Get Started Dashboard

Company

Contact Build an MCP App

Legal

Privacy Policy Terms of Use

© 2026 MCP App Store

All rights reserved.

GPT-5.4Undisclosed

92.36% accuracy

Llama-3.1-Nemotron-70B-Instruct-HF70B

87.38% accuracy

Gemini 2.5 ProUndisclosed

87.04% accuracy

Claude Sonnet 4.6Undisclosed

83.72% accuracy

GPT-4.1Undisclosed

83.06% accuracy

Llama-3.1-70B-Instruct70B

81.73% accuracy

79.40% accuracy

Gemini 3 ProUndisclosed

78.07% accuracy

78.07% accuracy

Llama-3.3-70B-Instruct70B

77.08% accuracy

DeepSeek-V3671B

76.74% accuracy

DeepSeek-R1671B

76.41% accuracy

DeepSeek-V3-0324671B

76.41% accuracy

o4-miniUndisclosed

76.08% accuracy

Claude Opus 4.6Undisclosed

74.09% accuracy

Gemini 1.5 ProUndisclosed

73.09% accuracy

DeepSeek Reasoner (V3.2)671B

72.76% accuracy

GPT-4oUndisclosed

72.43% accuracy

70.43% accuracy

Qwen2.5-72B-Instruct72B

64.12% accuracy

64.12% accuracy

o3-miniUndisclosed

62.13% accuracy

Gemini 2.5 FlashUndisclosed

58.80% accuracy

DeepSeek-R1-Distill-Qwen-32B32B

57.48% accuracy

Grok 4.20Undisclosed

55.48% accuracy