The Model Index
Up to four models

DeepSeek-V3.2 vs Qwen3.6 27B

On the index (GPT-4 = 100), DeepSeek-V3.2 scores 141 and Qwen3.6 27B 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 DeepSeek-V3.2
Presets
DeepSeek-V3.2
141125–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.26 / $0.38
Context164K
Core tests taken2 of 9
Qwen3.6 27B
141125–158
WeightsOpen
ReleasedApr 2026
Price in / out$0.32 / $3.2
Context262K
Core tests taken2 of 9

DeepSeek-V3.2 and Qwen3.6 27B are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 3.6× less.

Test by testthird-party results

DeepSeek-V3.2Qwen3.6 27B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestDeepSeek-V3.2Qwen3.6 27B
Reasoning & knowledge
GPQA Diamond (Epoch AI)83.4%85.9%
Maths
AIME-style maths (OTIS mock)87.8%91.1%
Agents
DTBench85.6%78.1%
LMCA28.8%34.5%

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

This page as a chartDownload PNG