token.app › Compare › Qwen3.5 397B A17B vs Gemini 3.6 Flash

Qwen3.5 397B A17B vs Gemini 3.6 Flash

Gemini 3.6 Flash leads on 3 of 3 shared benchmarks. Qwen3.5 397B A17B is 1.2× cheaper per token on a blended 3:1 basis. Gemini 3.6 Flash accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
Qwen3.5 397B A17BGemini 3.6 Flash
ProviderAlibabaGoogle
Input $/1M$0.500$0.750
Output $/1M$3.60$3.75
Blended $/1M$1.27$1.50
Context window262K1.0M
Max output236K66K
ReleasedFeb 2026Jul 2026
LicenceOpen weightsProprietary
GPQA Diamond 86.4% 94.1%
FrontierMath T1–3 31.2% 58.9%
OTIS Mock AIME 88.9% 94.2%
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 Qwen3.5 397B A17B if…
  • Costs less per token — $1.27 vs $1.50 blended
  • Open weights — self-hostable
Choose Gemini 3.6 Flash if…
  • Higher GPQA Diamond (94.1% vs 86.4%)
  • Higher FrontierMath T1–3 (58.9% vs 31.2%)
  • Higher OTIS Mock AIME (94.2% vs 88.9%)
  • Larger context window (1.0M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Qwen3.5 397B A17B or Gemini 3.6 Flash?
Across the 3 benchmarks both models have independently-run scores for, Qwen3.5 397B A17B leads on 0 and Gemini 3.6 Flash leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Qwen3.5 397B A17B cheaper than Gemini 3.6 Flash?
Qwen3.5 397B A17B is cheaper: $1.27 versus $1.50 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.750. Output alone: $3.60 vs $3.75.
What context windows do Qwen3.5 397B A17B and Gemini 3.6 Flash have?
Qwen3.5 397B A17B: 262,144 tokens. Gemini 3.6 Flash: 1,048,576 tokens.
Who makes Qwen3.5 397B A17B and Gemini 3.6 Flash?
Qwen3.5 397B A17B is made by Alibaba. Gemini 3.6 Flash is made by Google.
Related comparisons
Qwen3.5 397B A17B full details Gemini 3.6 Flash full details Qwen3.5 397B A17B vs Flint (free) Qwen3.5 397B A17B vs MiniMax M3.1 Flash (free) Qwen3.5 397B A17B vs DeepSeek V4.1 Flash 1017 Qwen3.5 397B A17B vs Glimpse Qwen3.5 397B A17B vs Xing4.0 29B A4B (free) Qwen3.5 397B A17B vs Beam 1.0 501B A23B