Compare AI models

Specifications
Parameters
—27B
Context window
1.05M256k
API pricing
Input price
$0.20—
Output price
$1.20—
Cached input price
$0.02—
Cheapest input
$0.10OpenAI—
Cheapest output
$0.60OpenAI—
$100OpenAI list price—
Benchmarks
GPQA Diamond
92.3%87.8%
MMMU-Pro
78.4%75.8%
Overview
CompanyOpenAIQwen
Release dateJun 26 2026Apr 22 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.6 Luna leads Qwen3.6-27B on 2 of the 2 benchmarks they both report (GPQA Diamond, MMMU-Pro). Only GPT-5.6 Luna has a verified first-party price for an available API: $0.20 per million input tokens and $1.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.6-27B. Qwen3.6-27B shipped 65 days before GPT-5.6 Luna, so benchmark comparisons should account for the intervening progress.

Context windows are 1.05M (GPT-5.6 Luna) vs 256k (Qwen3.6-27B). GPT-5.6 Luna is closed, while Qwen3.6-27B is open weight.

On GPQA Diamond, GPT-5.6 Luna leads at 92.3% vs Qwen3.6-27B at 87.8%. On MMMU-Pro, GPT-5.6 Luna leads at 78.4% vs Qwen3.6-27B at 75.8%.