AI Benchmark Model

Qwen3.8 27B (Non-reasoning)

Benchmark scores, pricing, speed, and model comparisons for Qwen3.8 27B (Non-reasoning).

Key scores

Intelligence34.7Index score
Coding44.6Index score
Speed55.9Tokens/sec
Blended Cost$1.13Per 1M tokens

Qwen3.8 27B (Non-reasoning) is an artificial intelligence model released by Alibaba on August 14, 2026. This model achieves an intelligence index of 34.7 and a coding index of 44.6, while its math index remains unknown. Performance metrics indicate an output speed of 55.877 tokens per second with a time to first token of 1.274 seconds. Benchmark results for the model include 0.818 on GPQA, 0.121 on HLE, 0.356 on SciCode, and 0.63 on LCR. Pricing for the model is structured at $0.50 per 1 million input tokens and $3.00 per 1 million output tokens, resulting in a blended cost of $1.13 per 1 million tokens.

Benchmark results

4 tracked benchmark rows for Qwen3.8 27B (Non-reasoning).

GPQA Reasoning
81.8%
LCR Other
63.0%
SciCode Other
35.6%
HLE Other
12.1%

Comments (0)

No comments yet

Be the first to share your thoughts!