Compare · ModelsLive · 2 picked · head to head
Qwen3 30B A3B Thinking 2507 vs Qwen3 Next 80B A3B Thinking
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3 Next 80B A3B Thinking wins on 5/6 benchmarks
Qwen3 Next 80B A3B Thinking wins 5 of 6 shared benchmarks. Leads in math · knowledge · coding.
Category leads
math·Qwen3 Next 80B A3B Thinkingknowledge·Qwen3 Next 80B A3B Thinkinglanguage·Qwen3 30B A3B Thinking 2507coding·Qwen3 Next 80B A3B Thinking
Hype vs Reality
Attention vs performance
Qwen3 30B A3B Thinking 2507
#26 by perf·no signal
Qwen3 Next 80B A3B Thinking
#32 by perf·no signal
Best value
Qwen3 30B A3B Thinking 2507
2.0x better value than Qwen3 Next 80B A3B Thinking
Qwen3 30B A3B Thinking 2507
275.8 pts/$
$0.24/M
Qwen3 Next 80B A3B Thinking
140.4 pts/$
$0.44/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 Next 80B A3B Thinking
OpenCompass · AIME2025
Qwen3 Next 80B A3B Thinking leads by +2.2
Qwen3 30B A3B Thinking 2507
86.8
Qwen3 Next 80B A3B Thinking
89.0
OpenCompass · GPQA-Diamond
Qwen3 Next 80B A3B Thinking leads by +6.9
Qwen3 30B A3B Thinking 2507
70.1
Qwen3 Next 80B A3B Thinking
77.0
OpenCompass · HLE
Qwen3 Next 80B A3B Thinking leads by +1.8
Qwen3 30B A3B Thinking 2507
11.7
Qwen3 Next 80B A3B Thinking
13.5
OpenCompass · IFEval
Qwen3 30B A3B Thinking 2507 leads by +0.2
Qwen3 30B A3B Thinking 2507
89.7
Qwen3 Next 80B A3B Thinking
89.5
OpenCompass · LiveCodeBenchV6
Qwen3 Next 80B A3B Thinking leads by +6.9
Qwen3 30B A3B Thinking 2507
59.4
Qwen3 Next 80B A3B Thinking
66.3
OpenCompass · MMLU-Pro
Qwen3 Next 80B A3B Thinking leads by +2.5
Qwen3 30B A3B Thinking 2507
79.5
Qwen3 Next 80B A3B Thinking
82.0
Full benchmark table
| Benchmark | Qwen3 30B A3B Thinking 2507 | Qwen3 Next 80B A3B Thinking |
|---|---|---|
OpenCompass · AIME2025 | 86.8 | 89.0 |
OpenCompass · GPQA-Diamond | 70.1 | 77.0 |
OpenCompass · HLE | 11.7 | 13.5 |
OpenCompass · IFEval | 89.7 | 89.5 |
OpenCompass · LiveCodeBenchV6 | 59.4 | 66.3 |
OpenCompass · MMLU-Pro | 79.5 | 82.0 |
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 Next 80B A3B Thinking | $0.10 | $0.78 | 131K tokens (~66 books) | $2.68 |
People also compared
Qwen3 30B A3B Thinking 2507 vs Qwen3.5 397B A17BQwen3.5 397B A17B vs Qwen3 Next 80B A3B ThinkingQwen3 30B A3B Thinking 2507 vs Qwen3.6 Plusgpt-oss-20b vs Qwen3 30B A3B Thinking 2507phi-3-small 7.4B vs Qwen3 30B A3B Thinking 2507GPT-5.4 Pro vs Qwen3 30B A3B Thinking 2507gpt-oss-20b (free) vs Qwen3 30B A3B Thinking 2507Qwen3.6 Plus vs Qwen3 Next 80B A3B Thinking