The Model Index
Up to four models

Qwen 3.5 Flash (hosted 35B-A3B) vs Qwen 3.6 Flash

On the index (GPT-4 = 100), Qwen 3.5 Flash (hosted 35B-A3B) scores 138 and Qwen 3.6 Flash 136. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Qwen 3.5 Flash (hosted 35B-A3B)
Presets
Qwen 3.5 Flash (hosted 35B-A3B)
138121–155
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken2 of 9
Qwen 3.6 Flash
136119–152
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9

Qwen 3.5 Flash (hosted 35B-A3B) and Qwen 3.6 Flash are too close to call (3 points apart, within the uncertainty), ahead on 0 of 2 shared core tests.

Test by testthird-party results

Qwen 3.5 Flash (hosted 35B-A3B)Qwen 3.6 Flash
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesFrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)AGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestQwen 3.5 Flash (hosted 35B-A3B)Qwen 3.6 Flash
Reasoning & knowledge
GPQA Diamond (Epoch AI)82.3%83.3%
SimpleQA Verified20.3%15.9%
Maths
FrontierMath (tiers 1-3)18.3%22.5%
AIME-style maths (OTIS mock)84.4%84.4%
Chess puzzles14.0%12.0%
FrontierMath (2025 set)6.2%10.3%
FrontierMath tier 4 (2025 set)0.0%0.0%
Agents
DTBench82.9%77.1%
LMCA29.1%31.0%
Mystery game puzzles20.0%18.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG