AI Model Release Tracker - Analytics

Claude Opus 5vsGPT-5.5-Pro

Claude Opus 5
GPT-5.5-Pro
Specifications
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
36%
Agentic coding
DeepSWE 1.1
68.8%
Agentic coding
FrontierCode v1.1 (Main)
53.4%
Next.js coding
Next.js Evals
83%
Agentic computer work
Frontier-Bench v0.1
43.3%
Web browsing
BrowseComp
90.8%Best
90.1%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
56.3%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
64.7%Best
57.2%
Novel problem-solving
ARC-AGI-3
30.2%
Advanced math
FrontierMath · Tier 1–3
52.4%
Advanced math
FrontierMath · Tier 4
39.6%
Biology
BioMysteryBench · hard
49.4%
Biology
BioMysteryBench · human solved
90.1%
Agentic computer use
OSWorld 2.0
70.6%
Business workflows
AutomationBench
26%
Agentic legal work
Harvey's Legal Agent Benchmark (Held-out)
11.7%
Health
HealthBench Professional
59.8%
Knowledge work
GDPval-AA v2
1861
Knowledge work
GDPval (win/tie rate)
82.3%
Overview
CompanyAnthropicOpenAI
Release dateJul 24 2026Apr 23 2026
AccessProprietaryProprietary

Which is better: Claude Opus 5 or GPT-5.5-Pro?

Claude Opus 5 leads GPT-5.5-Pro on 2 of the 2 benchmarks they both report (BrowseComp, Humanity's Last Exam). GPT-5.5-Pro shipped 92 days before Claude Opus 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 BrowseComp, Claude Opus 5 leads at 90.8% vs GPT-5.5-Pro at 90.1%. On Humanity's Last Exam · with tools, Claude Opus 5 leads at 64.7% vs GPT-5.5-Pro at 57.2%.

Frequently asked questions

Claude Opus 5 was released by Anthropic on Jul 24 2026.

GPT-5.5-Pro was released by OpenAI on Apr 23 2026.

Claude Opus 5 leads on Humanity's Last Exam · with tools — Claude Opus 5 64.7% vs GPT-5.5-Pro 57.2%.

Other comparisons