Compare AI models

Specifications
Parameters
—27B/35B/122B
Context window
400k256k
API pricing
Input price
$1.75—
Output price
$14.00—
Cached input price
$0.175—
Cheapest input
$0.875OpenAI—
Cheapest output
$7.00OpenAI—
$1,050OpenAI list price—
Benchmarks
SWE-Bench Verified
80%72%
BrowseComp
65.8%63.8%
Humanity's Last Exam · no tools
34.5%25.3%
Humanity's Last Exam · with tools
45.5%47.5%
GPQA Diamond
92.4%86.6%
OSWorld-Verified
47.3%58%
CharXiv Reasoning
82.1%77.2%
MMMU-Pro
79.5%76.9%
Overview
CompanyOpenAIQwen
Release dateDec 11 2025Feb 24 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.2 leads Qwen3.5 Medium on 6 of the 8 benchmarks they both report. Only GPT-5.2 has a verified first-party price for an available API: $1.75 per million input tokens and $14.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.5 Medium. GPT-5.2 shipped 75 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.2) vs 256k (Qwen3.5 Medium). GPT-5.2 is closed, while Qwen3.5 Medium is open weight.

On SWE-Bench Verified, GPT-5.2 leads at 80% vs Qwen3.5 Medium at 72%. On BrowseComp, GPT-5.2 leads at 65.8% vs Qwen3.5 Medium at 63.8%. On Humanity's Last Exam · no tools, GPT-5.2 leads at 34.5% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Qwen3.5 Medium leads at 47.5% vs GPT-5.2 at 45.5%. On GPQA Diamond, GPT-5.2 leads at 92.4% vs Qwen3.5 Medium at 86.6%. On OSWorld-Verified, Qwen3.5 Medium leads at 58% vs GPT-5.2 at 47.3%. On CharXiv Reasoning, GPT-5.2 leads at 82.1% vs Qwen3.5 Medium at 77.2%. On MMMU-Pro, GPT-5.2 leads at 79.5% vs Qwen3.5 Medium at 76.9%.