RLTasksby ulam.ai
Models / Qwen

Qwen / MODEL EVIDENCE

Qwen3-235B-A22B-Thinking (Jul 2025)

10 benchmarks · 11 observations · 10 sources · released 2025-07-25

Scores at a glance

10 benchmarks · large dot: Qwen3-235B-A22B-Thinking (Jul 2025); small dots: closest models where reported

GPQA Diamond ↗80.05%
9.2896.4

Qwen3-235B-A22B-Thinking (Jul 2025) · GPQA diamond · Best score (across scorers) · % ↗

SimpleQA Verified ↗40.44%
676

Qwen3-235B-A22B-Thinking (Jul 2025) · SimpleQA Verified · Best score (across scorers) · % ↗

Lech Mazur Writing ↗8.24 / 10
6.058.6

Qwen3-235B-A22B-Thinking (Jul 2025) · Lech Mazur Writing · Mean rubric score / 10 ↗

WeirdML (v2) ↗41.04%
1.7393.57

Qwen3-235B-A22B-Thinking (Jul 2025) · WeirdML · Accuracy · % ↗

1 more reported result

37.28% · Qwen3-235B-A22B-Thinking (Jul 2025) · WeirdML · Accuracy · % · Epoch AI · WeirdML ↗

LMCA ↗29.31%
2.7868.26

Qwen3-235B-A22B-Thinking (Jul 2025) · LMCA · Score · % ↗

DTBench ↗80.27%
41.6598.93

Qwen3-235B-A22B-Thinking (Jul 2025) · DTBench · Accuracy · % ↗

Closest models by score

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

7.0 percentile-point gap

3 of 4 shared benchmark comparisons

7.9 percentile-point gap

3 of 4 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 →

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. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  2. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  3. GPQA Diamond ↗

    Epoch AI

  4. Mystery Game Puzzles ↗

    Epoch AI

  5. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  6. SimpleQA Verified ↗

    Epoch AI

  7. AI benchmarks & capabilities ↗

    Epoch AI

  8. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

  9. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  10. WeirdML ↗

    Håvard Tveit Ihle

Names used in source tables

Qwen3-235B-A22B-Thinking (Jul 2025)