IFBench ↗76.60%
Qwen3.6 Max Preview · IFBench · AA implementation ↗
Qwen / MODEL EVIDENCE
Qwen3.6 Max Preview
17 benchmarks · 18 observations · 18 sources · released 2026-04-20
Scores at a glance
17 benchmarks · large dot: Qwen3.6 Max Preview; small dots: closest models where reported
Terminal-Bench Hard ↗43.94%
Qwen3.6 Max Preview · Terminal-Bench Hard ↗
τ²-Bench Telecom ↗95.91%
Qwen3.6 Max Preview · τ²-Bench Telecom ↗
GPQA Diamond ↗87.37%
Qwen 3.6 Max (Preview) · GPQA diamond · Best score (across scorers) · % ↗
Qwen 3.6 Max (Preview) · FrontierMath-2025-02-28-Private · Best score (across scorers) · % ↗
Qwen 3.6 Max (Preview) · FrontierMath-Tier-4-2025-07-01-Private · Best score (across scorers) · % ↗
Qwen 3.6 Max (Preview) · OTIS Mock AIME 2024-2025 · Best score (across scorers) · % ↗
SWE-bench Verified ↗76.65%
Qwen 3.6 Max (Preview) · SWE-Bench verified · Best score (across scorers) · % ↗
1 more reported result
72.8 % · Qwen 3.6 Max Preview (Mini-SWE-agent) · SWE-bench Verified · Score · Vals AI · SWE-bench Verified ↗
Qwen 3.6 Max (Preview) · SimpleQA Verified · Best score (across scorers) · % ↗
Qwen 3.6 Max (Preview) · Mystery Game Puzzles · Best score (across scorers) · % ↗
Qwen 3.6 Max (Preview) · SimpleBench · Score (AVG@5) · % ↗
LMCA ↗42.53%
Qwen 3.6 Max (Preview) · LMCA · Score · % ↗
DTBench ↗87.2%
Qwen 3.6 Max (Preview) · DTBench · Accuracy · % ↗
Text Arena (Coding) ↗1479.06 Elo
Qwen 3.6 Max (Preview) · WebDev Arena · Elo ↗
Epoch Capabilities Index (ECI) ↗149.41 ECI
Qwen 3.6 Max (Preview) · General ECI · 26 October 2026 fit ↗
CaseLaw v2 ↗47.91 %
Qwen 3.6 Max Preview · CaseLaw · Accuracy ↗
CorpFin v2 ↗66.47 %
Qwen 3.6 Max Preview · CorpFin · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Gemini 3.5 Flash →Google
10 of 12 shared benchmark comparisons
Claude Opus 4.5 →Anthropic
9 of 12 shared benchmark comparisons
Kimi K2.6 →Kimi
9 of 12 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.
- Arena leaderboard — WebDev evaluation ↗
- IFBench Benchmark | Artificial Analysis ↗
- 𝜏²-Bench Telecom Benchmark | Artificial Analysis ↗
- Terminal-Bench Hard Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- FrontierMath Tier 4 (v1, old) ↗
- FrontierMath Tiers 1-3 (v1, old) ↗
- GPQA Diamond ↗
- Mystery Game Puzzles ↗
- OTIS Mock AIME 2024-2025 ↗
- SimpleQA Verified ↗
- SimpleBench ↗
- SWE-bench Verified ↗
- AI benchmarks & capabilities ↗
- CaseLaw — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- SWE-bench Verified — evaluation methodology and results ↗
Names used in source tables
Qwen 3.6 Max (Preview) · Qwen 3.6 Max Preview · Qwen 3.6 Max Preview (Mini-SWE-agent) · Qwen3.6 Max Preview