Claude Opus 5.5vsGPT-5.4

Claude Opus 5.5
GPT-5.4
Specifications
Context window
1M
API pricing
Input price
$4.00$2.50
Output price
$20.00$15.00
Cached input price
$0.20$0.25
Cheapest input
$1.25OpenAI
Cheapest output
$7.50OpenAI
Benchmarks
Humanity's Last Exam · with tools
67.7%52.1%
Benchmarks
BullshitBench v2
48%
ProgramBench
0%
FrontierCode v1.1 (Main) · main split
54.4%
Next.js Evals
65%
Terminal-Bench 4.0
66.4%
Terminal-Bench 2.0
75.1%
Terminal-Bench-Science 0.1
58.7%
Expert-SWE (Internal)
68.5%
Toolathlon
54.6%
BrowseComp
82.7%
CyberGym
79%
ARC-AGI-2
73.95%
FrontierMath · Tier 1–3
47.6%
FrontierMath · Tier 4
27.1%
GPQA Diamond
92.8%
OSWorld 2.0
81.8%
OSWorld-Verified
75%
AutomationBench
40%
GDPval-AA v2.1
1846
GDPval (win/tie rate)
83%
Chartography · with tools
89%
Overview
CompanyAnthropicOpenAI
Release dateSep 22 2026Mar 5 2026
AccessProprietaryProprietary

Other comparisons

Claude Opus 5.5vsGemini 3.8 FlashGPT-5.4vsGemini 3.8 FlashClaude Opus 5.5vsMuse Spark 1.3GPT-5.4vsMuse Spark 1.3Claude Opus 5.5vsGrok 4.7GPT-5.4vsGrok 4.7Claude Opus 5.5vsDeepSeek-V4.1-FlashGPT-5.4vsDeepSeek-V4.1-FlashClaude Opus 5.5vsMistral Medium 3.5GPT-5.4vsMistral Medium 3.5Claude Opus 5.5vsKimi K3GPT-5.4vsKimi K3

Frequently asked questions

Claude Opus 5.5 leads GPT-5.4 on 1 of the 1 benchmark they both report (Humanity's Last Exam). GPT-5.4 is cheaper on both input and output: $2.50 vs $4.00 per million input tokens, and $15.00 vs $20.00 per million output tokens. GPT-5.4 shipped 201 days before Claude Opus 5.5, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Humanity's Last Exam · with tools, Claude Opus 5.5 leads at 67.7% vs GPT-5.4 at 52.1%.