GPT-6 SolvsGLM-4.6

GPT-6 Sol
GLM-4.6
Specifications
Parameters
355B
Context window
1.05M200k
API pricing
Input price
$2.00$0.60
Output price
$10.00$2.20
Cached input price
$0.20$0.11
Cheapest input
$0.43Venice
Cheapest output
$1.75Venice
Benchmarks
SWE-Bench Verified
68%
DeepSWE 1.1
68.8%
OSWorld 2.0
60.5%
Agent's Last Exam · pass@1
56.4%
AutomationBench
33.2%
Overview
CompanyOpenAIZ.ai
Release dateSep 22 2026Sep 30 2025
AccessProprietaryOpen Weight

Other comparisons

GPT-6 SolvsClaude Opus 5.5GLM-4.6vsClaude Opus 5.5GPT-6 SolvsGemini 3.8 FlashGLM-4.6vsGemini 3.8 FlashGPT-6 SolvsMuse Spark 1.3GLM-4.6vsMuse Spark 1.3GPT-6 SolvsGrok 4.7GLM-4.6vsGrok 4.7GPT-6 SolvsDeepSeek-V4.1-FlashGLM-4.6vsDeepSeek-V4.1-FlashGPT-6 SolvsMistral Medium 3.5GLM-4.6vsMistral Medium 3.5

Frequently asked questions

GPT-6 Sol and GLM-4.6 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4.6 is cheaper on both input and output: $0.60 vs $2.00 per million input tokens, and $2.20 vs $10.00 per million output tokens. Figures are base-tier rates. GLM-4.6 shipped 357 days before GPT-6 Sol, so benchmark comparisons should account for the intervening progress.

Context windows are 1.05M (GPT-6 Sol) vs 200k (GLM-4.6). GPT-6 Sol is proprietary, while GLM-4.6 is open weight.

Direct benchmark comparisons are unavailable — GPT-6 Sol and GLM-4.6 don't publish scores on any of the same benchmarks.