GPQA Diamond ↗72.6%
Qwen3-Max-Instruct · GPQA diamond · Best score (across scorers) · % ↗
Qwen / MODEL EVIDENCE
Qwen3 Max-Instruct
10 benchmarks · 10 observations · 10 sources · released 2025-09-24
Scores at a glance
10 benchmarks · large dot: Qwen3 Max-Instruct; small dots: closest models where reported
Qwen3-Max-Instruct · FrontierMath-Tiers-1-3-v2-Private · Best score (across scorers) · % ↗
MATH Level 5 ↗97.13%
Qwen3-Max-Instruct · MATH level 5 · Best score (across scorers) · % ↗
Qwen3-Max-Instruct · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
SimpleQA Verified ↗48.75%
Qwen3-Max-Instruct · SimpleQA Verified · Best score (across scorers) · % ↗
Qwen3-Max-Instruct · Mystery Game Puzzles · Best score (across scorers) · % ↗
Fiction.liveBench ↗66.7%
Qwen3-Max-Instruct · Fiction.LiveBench · 16k token score · % ↗
CL-bench ↗14.5%
Qwen3-Max-Instruct · CL-bench · Overall · % ↗
LMCA ↗28.27%
Qwen3-Max-Instruct · LMCA · Score · % ↗
DTBench ↗82.13%
Qwen3-Max-Instruct · DTBench · Accuracy · % ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
o1 →OpenAI
5 of 6 shared benchmark comparisons
GPT-5 mini (minimal) →OpenAI
4 of 6 shared benchmark comparisons
Qwen3.7 Flash →Qwen
4 of 6 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.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- CL-bench ↗
- FrontierMath Tiers 1-3 (v2) ↗
- GPQA Diamond ↗
- MATH Level 5 ↗
- Mystery Game Puzzles ↗
- OTIS Mock AIME 2024-2025 ↗
- SimpleQA Verified ↗
- Fiction.liveBench — March 14, 2025 benchmark release ↗
Names used in source tables
Qwen3-Max-Instruct