Compare · ModelsLive · 2 picked · head to head
Qwen3.6 Max Preview vs Qwen3.8 Max (0902)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.8 Max (0902) wins on 8/9 benchmarks
Qwen3.8 Max (0902) wins 8 of 9 shared benchmarks. Leads in arena · knowledge · general.
Category leads
arena·Qwen3.8 Max (0902)knowledge·Qwen3.8 Max (0902)general·Qwen3.8 Max (0902)math·Qwen3.8 Max (0902)
Hype vs Reality
Attention vs performance
Qwen3.6 Max Preview
#124 by perf·#1 by attention
Qwen3.8 Max (0902)
#87 by perf·#1 by attention
Best value
Qwen3.6 Max Preview
1.0x better value than Qwen3.8 Max (0902)
Qwen3.6 Max Preview
14.2 pts/$
$3.59/M
Qwen3.8 Max (0902)
13.8 pts/$
$4.00/M
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
9 benchmarks · 2 models
Qwen3.6 Max PreviewQwen3.8 Max (0902)
Chatbot Arena Elo · Coding
Qwen3.8 Max (0902) leads by +189.6
Qwen3.6 Max Preview
1481.5
Qwen3.8 Max (0902)
1671.2
Chatbot Arena Elo · Overall
Qwen3.8 Max (0902) leads by +21.3
Qwen3.6 Max Preview
1460.3
Qwen3.8 Max (0902)
1481.6
Chess Puzzles
Qwen3.8 Max (0902) leads by +27.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Qwen3.6 Max Preview
15.8
Qwen3.8 Max (0902)
43.2
Dtbench
Qwen3.8 Max (0902) leads by +8.0
Qwen3.6 Max Preview
78.7
Qwen3.8 Max (0902)
86.7
GPQA diamond
Qwen3.8 Max (0902) leads by +10.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen3.6 Max Preview
83.2
Qwen3.8 Max (0902)
94.0
Lmca
Qwen3.8 Max (0902) leads by +4.4
Qwen3.6 Max Preview
50.0
Qwen3.8 Max (0902)
54.4
Mystery Game Puzzles
Qwen3.8 Max (0902) leads by +20.9
Qwen3.6 Max Preview
10.8
Qwen3.8 Max (0902)
31.7
OTIS Mock AIME 2024-2025
Qwen3.8 Max (0902) leads by +8.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Qwen3.6 Max Preview
91.1
Qwen3.8 Max (0902)
99.4
SimpleQA Verified
Qwen3.6 Max Preview leads by +6.2
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Qwen3.6 Max Preview
52.0
Qwen3.8 Max (0902)
45.8
Full benchmark table
| Benchmark | Qwen3.6 Max Preview | Qwen3.8 Max (0902) |
|---|---|---|
Chatbot Arena Elo · Coding | 1481.5 | 1671.2 |
Chatbot Arena Elo · Overall | 1460.3 | 1481.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 15.8 | 43.2 |
Dtbench | 78.7 | 86.7 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 83.2 | 94.0 |
Lmca | 50.0 | 54.4 |
Mystery Game Puzzles | 10.8 | 31.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 91.1 | 99.4 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 52.0 | 45.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.03 | $6.16 | 262K tokens (~131 books) | $23.11 | |
| $2.00 | $6.00 | 1.0M tokens (~500 books) | $30.00 |