OpenCodePapers

agents-on-mcpatlas-public-500-tasks

Agents
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Kimi K3: Open Frontier Intelligence✓ Link84.2Kimi K3 Max2026-07-27
Hy4 preview✓ Link83.7Hy4 preview2026-08-28
Hy3✓ Link79.1Hy32026-07-02
GLM-5.2: Built for Long-Horizon Tasks✓ Link76.8GLM-5.22026-06-16
Muse Glimmer 30B: An On-Device Agentic Model✓ Link75.5Muse Glimmer-30B (High Reasoning)2026-10-17
MiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model✓ Link74.2MiniMax M32026-05-31
GLM-5.1: Towards Long-Horizon Tasks✓ Link71.8GLM-5.12026-04-03
Gemini 3.1 Pro: A smarter model for your most complex tasks69.2Gemini 3.1 Pro2026-02-19
GLM-5: From Vibe Coding to Agentic Engineering✓ Link67.8GLM-52026-02-11