MCPAtlas PublicBrowse 296

MCPAtlas Public

Can the model plan, use tools, and finish a multi-step task?

Version not specifiedExact reported variant
Agents7 ranked models11 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

7
RankModelBest scoreBest reported setting
1DeepSeek V4 ProDeepSeek74.2%high effortDeepSeek report3 values · 1 reportApr 26, 2026 · source
2Claude Opus 4.6Anthropic73.8%max effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
3GLM-5.1Z.ai71.8%Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source
4Gemini 3.1 ProGoogle69.2%high effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
5DeepSeek-V4-FlashDeepSeek69.0%max effortDeepSeek report3 values · 1 reportApr 26, 2026 · source
6GPT-5.4OpenAI67.2%xhigh effortDeepSeek report1 value · 1 reportApr 26, 2026 · source
7Kimi K2.6Moonshot AI66.6%Reported configurationDeepSeek report1 value · 1 reportApr 26, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model plan, use tools, and finish a multi-step task?

Agentic execution across tools, environments, or long-running workflows. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

Frontier comparison and across-modes table.

Method / source