Compare · ModelsLive · 2 picked · head to head
Qwen3 30B A3B Instruct 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 7/7 benchmarks
Qwen3.5 397B A17B wins 7 of 7 shared benchmarks. Leads in arena · math · knowledge.
Category leads
arena·Qwen3.5 397B A17Bmath·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 Instruct 2507
#77 by perf·#2 by attention
Qwen3.5 397B A17B
#48 by perf·#2 by attention
Best value
Qwen3 30B A3B Instruct 2507
15.5x better value than Qwen3.5 397B A17B
Qwen3 30B A3B Instruct 2507
458.5 pts/$
$0.12/M
Qwen3.5 397B A17B
29.6 pts/$
$2.02/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
7 benchmarks · 2 models
Qwen3 30B A3B Instruct 2507Qwen3.5 397B A17B
Chatbot Arena Elo · Overall
Qwen3.5 397B A17B leads by +59.1
Qwen3 30B A3B Instruct 2507
1382.7
Qwen3.5 397B A17B
1441.8
OpenCompass · AIME2025
Qwen3.5 397B A17B leads by +28.5
Qwen3 30B A3B Instruct 2507
63.8
Qwen3.5 397B A17B
92.3
OpenCompass · GPQA-Diamond
Qwen3.5 397B A17B leads by +24.8
Qwen3 30B A3B Instruct 2507
63.6
Qwen3.5 397B A17B
88.4
OpenCompass · HLE
Qwen3.5 397B A17B leads by +19.8
Qwen3 30B A3B Instruct 2507
7.7
Qwen3.5 397B A17B
27.5
OpenCompass · IFEval
Qwen3.5 397B A17B leads by +7.6
Qwen3 30B A3B Instruct 2507
83.9
Qwen3.5 397B A17B
91.5
OpenCompass · LiveCodeBenchV6
Qwen3.5 397B A17B leads by +44.3
Qwen3 30B A3B Instruct 2507
38.7
Qwen3.5 397B A17B
83.0
OpenCompass · MMLU-Pro
Qwen3.5 397B A17B leads by +13.7
Qwen3 30B A3B Instruct 2507
73.9
Qwen3.5 397B A17B
87.6
Full benchmark table
| Benchmark | Qwen3 30B A3B Instruct 2507 | Qwen3.5 397B A17B |
|---|---|---|
Chatbot Arena Elo · Overall | 1382.7 | 1441.8 |
OpenCompass · AIME2025 | 63.8 | 92.3 |
OpenCompass · GPQA-Diamond | 63.6 | 88.4 |
OpenCompass · HLE | 7.7 | 27.5 |
OpenCompass · IFEval | 83.9 | 91.5 |
OpenCompass · LiveCodeBenchV6 | 38.7 | 83.0 |
OpenCompass · MMLU-Pro | 73.9 | 87.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.05 | $0.19 | 262K tokens (~131 books) | $0.84 | |
| $0.55 | $3.50 | 262K tokens (~131 books) | $12.88 |