Compare · ModelsLive · 2 picked · head to head
Qwen3 Next 80B A3B Thinking vs o3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o3 wins on 5/5 benchmarks
o3 wins 5 of 5 shared benchmarks. Leads in knowledge · language · math.
Category leads
knowledge·o3language·o3math·o3reasoning·o3
Hype vs Reality
Attention vs performance
Qwen3 Next 80B A3B Thinking
#34 by perf·no signal
o3
#69 by perf·no signal
Best value
Qwen3 Next 80B A3B Thinking
12.7x better value than o3
Qwen3 Next 80B A3B Thinking
140.4 pts/$
$0.44/M
o3
11.0 pts/$
$5.00/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
5 benchmarks · 2 models
Qwen3 Next 80B A3B Thinkingo3
HELM · GPQA
o3 leads by +12.3
Qwen3 Next 80B A3B Thinking
63.0
o3
75.3
HELM · IFEval
o3 leads by +5.9
Qwen3 Next 80B A3B Thinking
81.0
o3
86.9
HELM · MMLU-Pro
o3 leads by +7.3
Qwen3 Next 80B A3B Thinking
78.6
o3
85.9
HELM · Omni-MATH
o3 leads by +24.7
Qwen3 Next 80B A3B Thinking
46.7
o3
71.4
HELM · WildBench
o3 leads by +5.4
Qwen3 Next 80B A3B Thinking
80.7
o3
86.1
Full benchmark table
| Benchmark | Qwen3 Next 80B A3B Thinking | o3 |
|---|---|---|
HELM · GPQA | 63.0 | 75.3 |
HELM · IFEval | 81.0 | 86.9 |
HELM · MMLU-Pro | 78.6 | 85.9 |
HELM · Omni-MATH | 46.7 | 71.4 |
HELM · WildBench | 80.7 | 86.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.10 | $0.78 | 131K tokens (~66 books) | $2.68 | |
| $2.00 | $8.00 | 200K tokens (~100 books) | $35.00 |