AI Benchmark Model

Qwen3.6 Max Preview

Benchmark scores, pricing, speed, and model comparisons for Qwen3.6 Max Preview.

Key scores

Intelligence51.8Index score
Coding44.9Index score
Speed36.6Tokens/sec
Blended Cost$2.92Per 1M tokens

Qwen3.6 Max Preview is an artificial intelligence model developed by Alibaba, released on April 20, 2026. The model records an intelligence index of 51.8 and a coding index of 44.9, while its math index remains unknown. Performance metrics indicate an output speed of 37.954 tokens per second with a time to first token of 2.154 seconds. Pricing for the model is set at $1.30 per 1 million input tokens and $7.80 per 1 million output tokens, resulting in a blended rate of $2.92 per 1 million tokens. Benchmark results include 0.888 on GPQA, 0.289 on HLE, 0.469 on SciCode, 0.766 on IFBench, 0.697 on LCR, 0.439 on TerminalBench Hard, and 0.959 on TAU2.

Benchmark results

7 tracked benchmark rows for Qwen3.6 Max Preview.

TAU2 Other
95.9%
GPQA Reasoning
88.8%
IFBench Other
76.6%
LCR Other
69.7%
SciCode Other
46.9%
TerminalBench Hard Other
43.9%
HLE Other
28.9%

Comments (0)

No comments yet

Be the first to share your thoughts!