AlibabaQwen3 Max Thinking (Preview)
- Released
- Nov 3, 2025
- Tracked since
- 2026-07-23
Intelligence index16.3Ranks 254 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageQwen3 Max Thinking (Preview)
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $1.20
- Output
- $6.00
- Cache read
- $0.240
Performance
- Output throughput
- 63 tokens/sec
- Time to first token
- 4.01s
- First answer token
- 35.70s
- End-to-end response
- 43.62s
History
2Intelligence index
25→16.3
Output
Unchanged across 62 days of records
Output throughput
55→63
Cheaper at this level
Models with a comparable intelligence index and a lower output price- DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeekIntelligence 18.9$0.200−97% - Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−97% - Hy3-preview (Non-reasoning)TencentIntelligence 17$0.210−97%
- Ling 3.0 Flash
InclusionAIIntelligence 24.9$0.220−96% - Ling-3.0-flash-VLInclusionAIIntelligence 24.6$0.220−96%