GPT-6 SolvsQwen3.8-Max

GPT-6 Sol
Qwen3.8-Max
Specifications
Parameters
2.4T
Context window
1.05M1M
API pricing
Input price
$2.00
Output price
$10.00
Cached input price
$0.20
Cheapest input
$2.00Alibaba
Cheapest output
$6.00Alibaba
Benchmarks
DeepSWE 1.1
68.8%56.6%
Benchmarks
BullshitBench v2
95%
SWE-Bench Pro
67.7%
PaperBench
93%
NL2Repo-Bench
55.9%
QwenSWEBench V2
55.1%
Terminal-Bench 3.0
11.3%
Terminal-Bench 2.1
86.6%
JobBench
53.4%
CoWorkBench
74.8%
Toolathlon-Verified
72.5%
Humanity's Last Exam · with tools
43.6%
OSWorld 2.0
60.5%
OSWorld-Verified
86.1%
Agent's Last Exam · pass@1
56.4%
AutomationBench
33.2%
CharXiv Reasoning
88.4%
BabyVision
82%
MMMU-Pro
82.3%
Overview
CompanyOpenAIQwen
Release dateSep 22 2026Aug 3 2026
AccessProprietaryProprietary

Other comparisons

GPT-6 SolvsClaude Opus 5.5Qwen3.8-MaxvsClaude Opus 5.5GPT-6 SolvsGemini 3.8 FlashQwen3.8-MaxvsGemini 3.8 FlashGPT-6 SolvsMuse Spark 1.3Qwen3.8-MaxvsMuse Spark 1.3GPT-6 SolvsGrok 4.7Qwen3.8-MaxvsGrok 4.7GPT-6 SolvsDeepSeek-V4.1-FlashQwen3.8-MaxvsDeepSeek-V4.1-FlashGPT-6 SolvsMistral Medium 3.5Qwen3.8-MaxvsMistral Medium 3.5

Frequently asked questions

GPT-6 Sol leads Qwen3.8-Max on 1 of the 1 benchmark they both report (DeepSWE 1.1). Only GPT-6 Sol has a verified first-party API price: $2.00 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Qwen3.8-Max. Qwen3.8-Max shipped 50 days before GPT-6 Sol, so benchmark comparisons should account for the intervening progress.

Context windows are 1.05M (GPT-6 Sol) vs 1M (Qwen3.8-Max).

On DeepSWE 1.1, GPT-6 Sol leads at 68.8% vs Qwen3.8-Max at 56.6%.