Loading...
Loading...
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.
Quality Index
31.4
93rd of 444
Top 21%
Coding Index
26.4
97th of 354
Top 27%
Math Index
80.7
61st of 268
Top 23%
Price/1M
$2.40
552nd cheapest
700% above median
Top 81%
Speed
32 tok/s
Top 57%
TTFT
1.76s
Context Window
262K
61st largest
Top 25%
Input
$1.20
per 1M tokens
Output
$6.00
per 1M tokens
Blended
$2.40
per 1M tokens
Cheaper than 19% of models. Median price is $0.30/1M tokens.
Daily
$2.40
Monthly
$72.00
32
tokens/sec
Faster than 43% of models
1.76
seconds
Faster than 16% of models
1.76
seconds
Faster than 30% of models
Market Median
45 tok/s
29% slower
Median TTFT
0.42s
320% slower
Throughput/Dollar
13
tok/s per $/1M
Speed Comparison
Context Window
262K
tokens
Larger than 75% of models
Max Output
33K
tokens
13% of context