Alibaba Models: Intelligence, Performance & Price
Qwen3.8 Max (0902)Qwen3.8 2.4T A95BQwen3.8-Flash-NextQwen3.8 27B (xhigh)Qwen3.8 27B (medium)Artificial Analysis Intelligence Index
Qwen3.5 Omni FlashQwen3 Next 80B A3BQwen3.6 35B A3B (non-reasoning)Qwen3.6 35B A3BQwen3.5 122B A10B (non-reasoning)Output speed
Per Intelligence Index Task
Artificial Analysis has benchmarked 89 models from Alibaba. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Alibaba is Qwen3.8 Max (0902) at 45.
- For output speed, the fastest model is Qwen3.5 Omni Flash at 233 t/s.
- For latency, Qwen3.5 9B (Non-reasoning) at 0.73s offers the lowest time to first answer token.
- For pricing, Qwen3.5 9B (Reasoning) at $0.21 offers the lowest cost per task. Prices vary up to 25x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All Alibaba Releases
Qwen3.8 Max (0902)
1 model
45
Highest Intelligence
Qwen3.8-Flash-Next
1 model
40
Highest Intelligence
Qwen3.8 27B
4 models
34
Highest Intelligence
Qwen3.8 2.4T A95B
1 model
40
Highest Intelligence
Qwen3.8 Max
1 model
40
Highest Intelligence
Qwen3.7 Plus
1 model
25
Highest Intelligence
Qwen3.7 Max
1 model
29
Highest Intelligence
Qwen3.6 27B
2 models
21
Highest Intelligence
Qwen3.6 Max Preview
1 model
28
Highest Intelligence
Qwen3.6 35B A3B
2 models
18
Highest Intelligence
Qwen3.6 Plus
1 model
27
Highest Intelligence
Qwen3.5 Omni Flash
1 model
12
Highest Intelligence
Qwen3.5 Omni Plus
1 model
20
Highest Intelligence
Qwen3.5 0.8B
2 models
6
Highest Intelligence
Qwen3.5 2B
2 models
7
Highest Intelligence
Qwen3.5 4B
2 models
13
Highest Intelligence
Qwen3.5 9B
2 models
13
Highest Intelligence
Qwen3.5 122B A10B
2 models
18
Highest Intelligence
Qwen3.5 27B
2 models
23
Highest Intelligence
Qwen3.5 35B A3B
2 models
19
Highest Intelligence
Qwen3.5 397B A17B
2 models
21
Highest Intelligence
Qwen3 Coder Next
1 model
9
Highest Intelligence
Qwen3 Max Thinking
1 model
21
Highest Intelligence
Qwen3 Max Thinking (Preview)
1 model
16
Highest Intelligence
Qwen3 VL 32B (Reasoning)
1 model
12
Highest Intelligence
Qwen3 VL 32B Instruct
1 model
8
Highest Intelligence
Qwen3 VL 4B (Reasoning)
1 model
7
Highest Intelligence
Qwen3 VL 4B Instruct
1 model
6
Highest Intelligence
Qwen3 VL 8B (Reasoning)
1 model
8
Highest Intelligence
Qwen3 VL 8B Instruct
1 model
7
Highest Intelligence
Qwen3 VL 30B A3B (Reasoning)
1 model
9
Highest Intelligence
Qwen3 VL 30B A3B Instruct
1 model
8
Highest Intelligence
Qwen3 Max
1 model
16
Highest Intelligence
Qwen3 VL 235B A22B (Reasoning)
1 model
13
Highest Intelligence
Qwen3 VL 235B A22B Instruct
1 model
10
Highest Intelligence
Qwen3 Omni 30B A3B (Reasoning)
1 model
8
Highest Intelligence
Qwen3 Omni 30B A3B Instruct
1 model
6
Highest Intelligence
Qwen3 Next 80B A3B (Reasoning)
1 model
11
Highest Intelligence
Qwen3 Next 80B A3B Instruct
1 model
10
Highest Intelligence
Qwen3 Max (Preview)
1 model
13
Highest Intelligence
Qwen3 4B 2507 Instruct
1 model
7
Highest Intelligence
Qwen3 4B 2507 (Reasoning)
1 model
9
Highest Intelligence
Qwen3 Coder 30B A3B Instruct
1 model
10
Highest Intelligence
Qwen3 30B A3B 2507 (Reasoning)
1 model
10
Highest Intelligence
Qwen3 30B A3B 2507 Instruct
1 model
8
Highest Intelligence
Qwen3 235B A22B 2507 (Reasoning)
1 model
13
Highest Intelligence
Qwen3 Coder 480B A35B Instruct
1 model
12
Highest Intelligence
Qwen3 235B A22B 2507 Instruct
1 model
12
Highest Intelligence
Qwen3 0.6B
2 models
5
Highest Intelligence
Qwen3 1.7B
2 models
5
Highest Intelligence
Qwen3 14B
2 models
7
Highest Intelligence
Qwen3 235B A22B
2 models
9
Highest Intelligence
Qwen3 30B A3B
2 models
8
Highest Intelligence
Qwen3 32B
2 models
7
Highest Intelligence
Qwen3 4B
2 models
7
Highest Intelligence
Qwen3 8B
2 models
6
Highest Intelligence
QwQ 32B
1 model
9
Highest Intelligence
Qwen2.5 Max
1 model
8
Highest Intelligence
QwQ 32B-Preview
1 model
8
Highest Intelligence
Qwen2.5 Turbo
1 model
6
Highest Intelligence
Qwen2.5 Coder Instruct 32B
1 model
7
Highest Intelligence
Qwen2.5 Instruct 72B
1 model
8
Highest Intelligence
Qwen2.5 Coder Instruct 7B
1 model
6
Highest Intelligence
Qwen2.5 Instruct 32B
1 model
7
Highest Intelligence
Qwen2 Instruct 72B
1 model
6
Highest Intelligence
Qwen1.5 Chat 110B
1 model
6
Highest Intelligence
Qwen Chat 72B
1 model
5
Highest Intelligence
Qwen Chat 14B
1 model
5
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 Max (0902) | Alibaba | 45 | - | 984k | $1.2 | 37 | Not available | | |
| Qwen3.8 Max | Alibaba | 40 | - | 1M | $1.2 | 37 | Not available | | |
| Qwen3.8 2.4T A95B | Alibaba | 40 | 2.4T 95B active at inference time | 262k | $1.2 | 38 |    +3 | ||
| Qwen3.8-Flash-Next | Alibaba | 40 | 180B 6B active at inference time | 256k | $0.1 | 53 | | ||
| Qwen3.8 27B (Xhigh) | Alibaba | 34 | 27B | 256k | $0.5 | 42 |  +6 | ||
| Qwen3.7 Max | Alibaba | 29 | - | 1M | $1.6 | 206 | Not available | | |
| Qwen3.6 Max Preview | Alibaba | 28 | - | 256k | - | - | Not available | - | |
| Qwen3.8 27B (Medium) | Alibaba | 28 | 27B | 256k | $0.5 | 44 | | ||
| Qwen3.6 Plus | Alibaba | 27 | - | 1M | $0.4 | 56 | Not available | | |
| Qwen3.8 27B (Low) | Alibaba | 26 | 27B | 256k | $0.5 | 45 | | ||
| Qwen3.7 Plus | Alibaba | 25 | - | 1M | $0.3 | 56 | Not available | | |
| Qwen3.5 27B (Reasoning) | Alibaba | 23 | 27.8B | 262k | $0.5 | 78 |   +2 | ||
| Qwen3.5 397B A17B (Non-reasoning) | Alibaba | 21 | 397B 17B active at inference time | 262k | $0.9 | 56 |  +2 | ||
| Qwen3.6 27B (Reasoning) | Alibaba | 21 | 27.8B | 262k | $0.9 | 56 |  | ||
| Qwen3 Max Thinking | Alibaba | 21 | - | 256k | - | - | Not available | - | |
| Qwen3.5 Omni Plus | Alibaba | 20 | - | 256k | $0.8 | 84 | Not available | | |
| Qwen3.8 27B (Non-reasoning) | Alibaba | 20 | 27B | 256k | $0.5 | 43 |   +3 | ||
| Qwen3.6 27B (Non-reasoning) | Alibaba | 20 | 27.8B | 262k | $0.9 | 56 | | ||
| Qwen3.5 27B (Non-reasoning) | Alibaba | 19 | 27.8B | 262k | $0.5 | 82 | | ||
| Qwen3.5 35B A3B (Reasoning) | Alibaba | 19 | 36B 3B active at inference time | 262k | $0.4 | 150 | +2 | ||
| Qwen3.5 397B A17B (Reasoning) | Alibaba | 18 | 397B 17B active at inference time | 262k | $0.9 | 55 |  +3 | ||
| Qwen3.6 35B A3B (Reasoning) | Alibaba | 18 | 36B 3B active at inference time | 262k | $0.6 | 139 | +5 | ||
| Qwen3.5 122B A10B (Non-reasoning) | Alibaba | 18 | 125B 10B active at inference time | 262k | $0.7 | 139 | | ||
| Qwen3 Max Thinking (Preview) | Alibaba | 16 | - | 262k | - | - | Not available | - | |
| Qwen3 Max | Alibaba | 16 | - | 262k | - | - | Not available | - | |
| Qwen3.5 122B A10B (Reasoning) | Alibaba | 16 | 125B 10B active at inference time | 262k | $0.7 | 131 | | ||
| Qwen3.6 35B A3B (Non-reasoning) | Alibaba | 15 | 36B 3B active at inference time | 262k | $0.6 | 154 |  +4 | ||
| Qwen3.5 35B A3B (Non-reasoning) | Alibaba | 15 | 36B 3B active at inference time | 262k | $0.4 | 168 | | ||
| Qwen3 VL 235B A22B (Reasoning) | Alibaba | 13 | 235B 22B active at inference time | 262k | - | - | - | ||
| Qwen3.5 9B (Non-reasoning) | Alibaba | 13 | 9.7B | 262k | $0.2 | 104 | | ||
| Qwen3.5 4B (Reasoning) | Alibaba | 13 | 4.7B | 262k | $0.0 | 10 | | ||
| Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 13 | 235B 22B active at inference time | 256k | $0.4 | 134 | | ||
| Qwen3 Max (Preview) | Alibaba | 13 | - | 262k | - | - | Not available | - | |
| Qwen3.5 Omni Flash | Alibaba | 12 | - | 256k | $0.2 | 233 | Not available | | |
| Qwen3 235B A22B 2507 Instruct | Alibaba | 12 | 235B 22B active at inference time | 256k | $0.3 | 47 |  +4 | ||
| Qwen3 Coder 480B A35B Instruct | Alibaba | 12 | 480B 35B active at inference time | 262k | $0.4 | 109 |   | ||
| Qwen3 VL 32B (Reasoning) | Alibaba | 12 | 33.4B | 256k | - | - | - | ||
| Qwen3 Next 80B A3B (Reasoning) | Alibaba | 11 | 80B 3B active at inference time | 262k | $0.3 | 155 | | ||
| Qwen3.5 9B (Reasoning) | Alibaba | 11 | 9.7B | 262k | $0.1 | 59 | | ||
| Qwen3.5 4B (Non-reasoning) | Alibaba | 11 | 4.7B | 262k | $0.0 | 8 | | ||
| Qwen3 VL 235B A22B Instruct | Alibaba | 10 | 235B 22B active at inference time | 262k | $0.3 | 34 | | ||
| Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 10 | 30.5B 3.3B active at inference time | 262k | $0.5 | - | - | ||
| Qwen3 Next 80B A3B Instruct | Alibaba | 10 | 80B 3B active at inference time | 262k | $0.2 | 115 |  | ||
| Qwen3 Coder 30B A3B Instruct | Alibaba | 10 | 30.5B 3.3B active at inference time | 262k | $0.2 | 156 | | ||
| Qwen3 235B A22B (Reasoning) | Alibaba | 9 | 235B 22B active at inference time | 33k | - | - | - | ||
| QwQ 32B | Alibaba | 9 | 32.8B | 131k | - | - | - | ||
| Qwen3 VL 30B A3B (Reasoning) | Alibaba | 9 | 30B 3B active at inference time | 256k | $0.5 | - | | ||
| Qwen3 Coder Next | Alibaba | 9 | 79.7B 3B active at inference time | 256k | $0.4 | 75 | | ||
| Qwen3 4B 2507 (Reasoning) | Alibaba | 9 | 4.0B | 262k | - | - | - | ||
| Qwen3 VL 32B Instruct | Alibaba | 8 | 33.4B | 256k | - | - | - | ||
| Qwen3 235B A22B (Non-reasoning) | Alibaba | 8 | 235B 22B active at inference time | 33k | - | - | - | ||
| Qwen3 VL 8B (Reasoning) | Alibaba | 8 | 8.8B | 256k | - | - | - | ||
| Qwen2.5 Max | Alibaba | 8 | - | 32k | - | - | Not available | - | |
| Qwen3 VL 30B A3B Instruct | Alibaba | 8 | 30B 3B active at inference time | 256k | $0.4 | 27 | | ||
| Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 8 | 35.3B 3B active at inference time | 66k | $0.3 | 101 | | ||
| Qwen2.5 Instruct 72B | Alibaba | 8 | 72B | 131k | $0.5 | 28 | | ||
| Qwen3 30B A3B (Reasoning) | Alibaba | 8 | 30.5B 3.3B active at inference time | 33k | $0.2 | 132 | | ||
| QwQ 32B-Preview | Alibaba | 8 | 32.8B | 33k | - | - | - | ||
| Qwen3 30B A3B 2507 Instruct | Alibaba | 8 | 30.5B 3.3B active at inference time | 262k | $0.2 | 45 | | ||
| Qwen3 32B (Non-reasoning) | Alibaba | 7 | 32.8B | 33k | $0.2 | 64 |  | ||
| Qwen3 VL 8B Instruct | Alibaba | 7 | 8.8B | 256k | - | - | - | ||
| Qwen3 4B (Reasoning) | Alibaba | 7 | 4.0B | 32k | - | - | - | ||
| Qwen3 32B (Reasoning) | Alibaba | 7 | 32.8B | 33k | $0.3 | 27 | | ||
| Qwen3 VL 4B (Reasoning) | Alibaba | 7 | 4.4B | 256k | - | - | - | ||
| Qwen3.5 2B (Reasoning) | Alibaba | 7 | 2.3B | 262k | - | - | - | ||
| Qwen2.5 Instruct 32B | Alibaba | 7 | 32B | 128k | - | - | - | ||
| Qwen3 4B 2507 Instruct | Alibaba | 7 | 4.0B | 262k | - | - | - | ||
| Qwen2.5 Coder Instruct 32B | Alibaba | 7 | 32B | 131k | - | - | - | ||
| Qwen3 14B (Non-reasoning) | Alibaba | 7 | 14.8B | 33k | $0.1 | 52 | | ||
| Qwen3 30B A3B (Non-reasoning) | Alibaba | 7 | 30.5B 3.3B active at inference time | 33k | $0.2 | 133 | | ||
| Qwen3 4B (Non-reasoning) | Alibaba | 7 | 4.0B | 32k | - | - | - | ||
| Qwen2.5 Turbo | Alibaba | 6 | - | 1M | $0.0 | - | Not available | | |
| Qwen3 14B (Reasoning) | Alibaba | 6 | 14.8B | 33k | $0.1 | 48 | | ||
| Qwen2 Instruct 72B | Alibaba | 6 | 72B | 131k | - | - | - | ||
| Qwen3.5 2B (Non-reasoning) | Alibaba | 6 | 2.3B | 262k | - | - | - | ||
| Qwen3.5 0.8B (Reasoning) | Alibaba | 6 | 0.9B | 262k | - | - | - | ||
| Qwen3 Omni 30B A3B Instruct | Alibaba | 6 | 35.3B 3B active at inference time | 66k | $0.3 | 96 | | ||
| Qwen3 8B (Non-reasoning) | Alibaba | 6 | 8.2B | 131k | $0.2 | - | | ||
| Qwen2.5 Coder Instruct 7B | Alibaba | 6 | 7.6B | 131k | - | - | - | ||
| Qwen3 VL 4B Instruct | Alibaba | 6 | 4.4B | 256k | - | - | - | ||
| Qwen1.5 Chat 110B | Alibaba | 6 | 110B | 32k | - | - | - | ||
| Qwen Chat 72B | Alibaba | 5 | 72B | 34k | - | - | - | ||
| Qwen3.5 0.8B (Non-reasoning) | Alibaba | 5 | 0.9B | 262k | - | - | - | ||
| Qwen3 1.7B (Reasoning) | Alibaba | 5 | 2.0B | 32k | - | - | - | ||
| Qwen3 8B (Reasoning) | Alibaba | 5 | 8.2B | 131k | - | - | - | ||
| Qwen Chat 14B | Alibaba | 5 | 14B | 8k | - | - | - | ||
| Qwen3 1.7B (Non-reasoning) | Alibaba | 5 | 2.0B | 32k | - | - | - | ||
| Qwen3 0.6B (Non-reasoning) | Alibaba | 5 | 0.8B | 32k | - | - | - | ||
| Qwen3 0.6B (Reasoning) | Alibaba | 5 | 0.8B | 32k | - | - | - |