Claude Opus 5.5vsGPT-4

Claude Opus 5.5
GPT-4
Specifications
Context window
1M8k
API pricing
Input price
$4.00$30.00
Output price
$20.00$60.00
Cached input price
$0.20
Cheapest input
$30.00Azure
Cheapest output
$60.00Azure
Benchmarks
FrontierCode v1.1 (Main) · main split
54.4%
HumanEval
67%
Terminal-Bench 4.0
66.4%
Terminal-Bench-Science 0.1
58.7%
Humanity's Last Exam · with tools
67.7%
MMLU
86.4%
GSM8K
92%
OSWorld 2.0
81.8%
AutomationBench
40%
GDPval-AA v2.1
1846
Chartography · with tools
89%
Overview
CompanyAnthropicOpenAI
Release dateSep 22 2026Mar 14 2023
AccessProprietaryProprietary

Other comparisons

Claude Opus 5.5vsGemini 3.8 FlashGPT-4vsGemini 3.8 FlashClaude Opus 5.5vsMuse Spark 1.3GPT-4vsMuse Spark 1.3Claude Opus 5.5vsGrok 4.7GPT-4vsGrok 4.7Claude Opus 5.5vsDeepSeek-V4.1-FlashGPT-4vsDeepSeek-V4.1-FlashClaude Opus 5.5vsMistral Medium 3.5GPT-4vsMistral Medium 3.5Claude Opus 5.5vsKimi K3GPT-4vsKimi K3

Frequently asked questions

Claude Opus 5.5 and GPT-4 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude Opus 5.5 is cheaper on both input and output: $4.00 vs $30.00 per million input tokens, and $20.00 vs $60.00 per million output tokens. GPT-4 shipped 1288 days before Claude Opus 5.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Opus 5.5) vs 8k (GPT-4).

Direct benchmark comparisons are unavailable — Claude Opus 5.5 and GPT-4 don't publish scores on any of the same benchmarks.