The Model Index
Up to four models

Qwen3.6-Plus vs Qwen 3.5 Plus (hosted 397B-A17B)

On the index (GPT-4 = 100), Qwen3.6-Plus scores 145 and Qwen 3.5 Plus (hosted 397B-A17B) 141. 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 Qwen3.6-Plus
Presets
Qwen3.6-Plus
145128–162
WeightsClosed
ReleasedApr 2026
Price in / out$0.33 / $1.95
Context1M
Core tests taken4 of 9
Qwen 3.5 Plus (hosted 397B-A17B)
141124–158
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken1 of 9

Qwen3.6-Plus and Qwen 3.5 Plus (hosted 397B-A17B) are too close to call (4 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Qwen3.6-PlusQwen 3.5 Plus (hosted 397B-A17B)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProCL-benchCL-benchSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-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)CODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMortgageTaxMortgageTax
Every result as a table
TestQwen3.6-PlusQwen 3.5 Plus (hosted 397B-A17B)
Reasoning & knowledge
GPQA Diamond (Epoch AI)88.4%84.9%
GPQA Diamond (Vals AI)87.4%87.4%
MMLU Pro87.7%87.2%
MMMU Pro84.2%22.8%
CL-bench20.3%19.8%
SimpleQA Verified44.1%25.4%
Maths
AIME-style maths (OTIS mock)93.3%86.7%
Chess puzzles16.0%9.0%
FrontierMath (2025 set)26.2%21.0%
FrontierMath tier 4 (2025 set)8.3%2.1%
Coding
LiveCodeBench86.0%85.3%
SWE-bench73.4%71.2%
Vibe Code Bench v1.125.6%15.7%
Agents
DTBench81.9%80.5%
LMCA33.1%36.4%
Mystery game puzzles12.0%17.0%
Professional work
CorpFin v261.9%65.3%
LegalBench84.2%85.1%
MortgageTax68.0%60.8%

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

This page as a chartDownload PNG