LIVE INTELLIGENCE · part of the Xentir AI Index

Claude Opus 5 vs GPT-5.5

Name: Claude Opus 5 vs GPT-5.5 — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Claude Opus 5 · Anthropic, released 2026-07-24
GPT-5.5 · OpenAI, released 2026-04-23

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-10 · Methodology · Data Sources

GPT-5.5 leads on more of the 5 benchmarks where both are measured — Claude Opus 5 on 1, GPT-5.5 on 4. The remaining 4 of 9 tracked benchmarks cannot be compared: 3 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Claude Opus 5 leads on 1, GPT-5.5 leads on 4.

Benchmark	Claude Opus 5	GPT-5.5	Leads
Epoch Capabilities Index (ECI)	162.6	159.1	Claude Opus 5
SWE-bench Verified	Not measured	0.806 (xhigh-pre-release)	Comparison unavailable — Claude Opus 5 has no published result
GPQA Diamond	0.939 (max)	0.940 (xhigh-pre-release)	GPT-5.5
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.989 (max)	1.000 (xhigh-pre-release)	GPT-5.5
FrontierMath	Not measured	0.517 (xhigh-pre-release)	Comparison unavailable — Claude Opus 5 has no published result
FrontierMath Tier 4	Not measured	0.354 (xhigh-pre-release)	Comparison unavailable — Claude Opus 5 has no published result
SimpleQA Verified	0.599 (max)	0.630 (xhigh)	GPT-5.5
Chess Puzzles	0.420 (max)	0.540 (xhigh-pre-release)	GPT-5.5

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

What remains uncertain

Claude Opus 5 has no published result on FrontierMath, FrontierMath Tier 4, SWE-bench Verified.
1 tracked benchmark has no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Reference price

Per 1M tokens	Claude Opus 5	GPT-5.5
Output	$25.00 stale	$30.00

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

Claude Opus 5 → · GPT-5.5 → · the full AI Model Rankings table