Compare · ModelsLive · 2 picked · head to head
Qwen3 30B A3B Thinking 2507 vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.5 397B A17B wins on 6/6 benchmarks
Qwen3.5 397B A17B wins 6 of 6 shared benchmarks. Leads in math · knowledge · language.
Category leads
math·Qwen3.5 397B A17Bknowledge·Qwen3.5 397B A17Blanguage·Qwen3.5 397B A17Bcoding·Qwen3.5 397B A17B
Hype vs Reality
Attention vs performance
Qwen3 30B A3B Thinking 2507
#26 by perf·no signal
Qwen3.5 397B A17B
#3 by perf·no signal
Best value
Qwen3 30B A3B Thinking 2507
4.8x better value than Qwen3.5 397B A17B
Qwen3 30B A3B Thinking 2507
275.8 pts/$
$0.24/M
Qwen3.5 397B A17B
57.4 pts/$
$1.36/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
6 benchmarks · 2 models
Qwen3 30B A3B Thinking 2507Qwen3.5 397B A17B
OpenCompass · AIME2025
Qwen3.5 397B A17B leads by +5.5
Qwen3 30B A3B Thinking 2507
86.8
Qwen3.5 397B A17B
92.3
OpenCompass · GPQA-Diamond
Qwen3.5 397B A17B leads by +18.3
Qwen3 30B A3B Thinking 2507
70.1
Qwen3.5 397B A17B
88.4
OpenCompass · HLE
Qwen3.5 397B A17B leads by +15.8
Qwen3 30B A3B Thinking 2507
11.7
Qwen3.5 397B A17B
27.5
OpenCompass · IFEval
Qwen3.5 397B A17B leads by +1.8
Qwen3 30B A3B Thinking 2507
89.7
Qwen3.5 397B A17B
91.5
OpenCompass · LiveCodeBenchV6
Qwen3.5 397B A17B leads by +23.6
Qwen3 30B A3B Thinking 2507
59.4
Qwen3.5 397B A17B
83.0
OpenCompass · MMLU-Pro
Qwen3.5 397B A17B leads by +8.1
Qwen3 30B A3B Thinking 2507
79.5
Qwen3.5 397B A17B
87.6
Full benchmark table
| Benchmark | Qwen3 30B A3B Thinking 2507 | Qwen3.5 397B A17B |
|---|---|---|
OpenCompass · AIME2025 | 86.8 | 92.3 |
OpenCompass · GPQA-Diamond | 70.1 | 88.4 |
OpenCompass · HLE | 11.7 | 27.5 |
OpenCompass · IFEval | 89.7 | 91.5 |
OpenCompass · LiveCodeBenchV6 | 59.4 | 83.0 |
OpenCompass · MMLU-Pro | 79.5 | 87.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Qwen3 30B A3B Thinking 2507 | $0.08 | $0.40 | 131K tokens (~66 books) | $1.60 |
| Qwen3.5 397B A17B | $0.39 | $2.34 | 262K tokens (~131 books) | $8.78 |
People also compared
GPT-5 Chat vs Qwen3.5 397B A17BClaude Mythos Preview vs Qwen3.5 397B A17BDeepSeek V3.2 Speciale vs Qwen3.5 397B A17BClaude Instant vs Qwen3.5 397B A17BQwen3.5 397B A17B vs Step 3.5 FlashDeepSeek-V2 (MoE-236B, May 2024) vs Qwen3.5 397B A17BMiMo-V2-Flash vs Qwen3.5 397B A17BGPT-5.1-Codex-Max vs Qwen3.5 397B A17B