token.app › Compare › Qwen3.5 397B A17B vs MiniMax M3
Qwen3.5 397B A17B vs MiniMax M3
Qwen3.5 397B A17B and MiniMax M3 split the 2 shared benchmarks evenly. MiniMax M3 is 2.4× cheaper per token on a blended 3:1 basis. MiniMax M3 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3.5 397B A17B | MiniMax M3 | |
|---|---|---|
| Provider | Alibaba | MiniMax |
| Input $/1M | $0.500 | $0.300 |
| Output $/1M | $3.60 | $1.20 |
| Blended $/1M | $1.27 | $0.525 |
| Context window | 262K | 1.0M |
| Max output | 236K | 512K |
| Released | Feb 2026 | May 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 86.4% | 90.9% |
| OTIS Mock AIME | 88.9% | 71.1% |
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…
- Higher OTIS Mock AIME (88.9% vs 71.1%)
Choose MiniMax M3 if…
- Costs less per token — $0.525 vs $1.27 blended
- Higher GPQA Diamond (90.9% vs 86.4%)
- Larger context window (1.0M)
- Newer model (released May 2026)
FAQ
Which is better, Qwen3.5 397B A17B or MiniMax M3?
Across the 2 benchmarks both models have independently-run scores for, Qwen3.5 397B A17B leads on 1 and MiniMax M3 leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Qwen3.5 397B A17B cheaper than MiniMax M3?
MiniMax M3 is cheaper: $0.525 versus $1.27 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.300. Output alone: $3.60 vs $1.20.
What context windows do Qwen3.5 397B A17B and MiniMax M3 have?
Qwen3.5 397B A17B: 262,144 tokens. MiniMax M3: 1,048,576 tokens.
Who makes Qwen3.5 397B A17B and MiniMax M3?
Qwen3.5 397B A17B is made by Alibaba. MiniMax M3 is made by MiniMax.
Related comparisons