token.app › Compare › Qwen3 235B A22B vs DeepSeek V3.2

Qwen3 235B A22B vs DeepSeek V3.2

DeepSeek V3.2 leads on 1 of 1 shared benchmarks. DeepSeek V3.2 is 2.7× cheaper per token on a blended 3:1 basis. DeepSeek V3.2 accepts the larger context window (164K).

Head to head
Blended price uses a 3:1 input:output mix
Qwen3 235B A22BDeepSeek V3.2
ProviderAlibabaDeepSeek
Input $/1M$0.455$0.260
Output $/1M$1.82$0.380
Blended $/1M$0.796$0.290
Context window131K164K
Max output8K164K
ReleasedApr 2025Dec 2025
LicenceOpen weightsOpen weights
GPQA Diamond 70.7% 71.2%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Qwen3 235B A22B if…
  • No clear advantage on the data we hold.
Choose DeepSeek V3.2 if…
  • Costs less per token — $0.290 vs $0.796 blended
  • Higher GPQA Diamond (71.2% vs 70.7%)
  • Larger context window (164K)
  • Newer model (released Dec 2025)
FAQ
Which is better, Qwen3 235B A22B or DeepSeek V3.2?
Across the 1 benchmark both models have independently-run scores for, Qwen3 235B A22B leads on 0 and DeepSeek V3.2 leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Qwen3 235B A22B cheaper than DeepSeek V3.2?
DeepSeek V3.2 is cheaper: $0.290 versus $0.796 per million tokens blended at 3:1 input:output. Input alone: $0.455 vs $0.260. Output alone: $1.82 vs $0.380.
What context windows do Qwen3 235B A22B and DeepSeek V3.2 have?
Qwen3 235B A22B: 131,072 tokens. DeepSeek V3.2: 163,840 tokens.
Who makes Qwen3 235B A22B and DeepSeek V3.2?
Qwen3 235B A22B is made by Alibaba. DeepSeek V3.2 is made by DeepSeek.
Related comparisons