RLTasksby ulam.ai
Models / Qwen

Qwen / MODEL EVIDENCE

Qwen3 Max-Thinking

15 benchmarks · 16 observations · 1 sources

Scores at a glance

15 benchmarks · large dot: Qwen3 Max-Thinking; small dots: closest models where reported

IFEval ↗93.4
90.994.8

Qwen3-Max-Thinking · IFEval · Qwen report ↗

BFCL V4 ↗67.7
63.177.5

Qwen3-Max-Thinking · BFCL-V4 · Qwen report ↗

MCPMark ↗33.5
29.557.5

Qwen3-Max-Thinking · MCP-Mark · original release · Qwen report ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

30.0 percentile-point gap

15 of 15 shared benchmark comparisons

46.0 percentile-point gap

15 of 15 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Reports featuring this model

Qwen3.5 · earlier-2026 baseline · Qwen →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Qwen/Qwen3.5-397B-A17B · Hugging Face ↗

    Qwen Team

Names used in source tables

Qwen3-Max-Thinking