LIVE INTELLIGENCE · part of the Xentir AI Index

Claude 3 Opus vs GPT-4 (Mar 2023)

Name: Claude 3 Opus vs GPT-4 (Mar 2023) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Claude 3 Opus · Anthropic, released 2024-02-29
GPT-4 (Mar 2023) · OpenAI, released 2023-03-14

“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 2026-09-09 · Methodology · Data Sources

Claude 3 Opus leads on more of the 3 benchmarks where both are measured — Claude 3 Opus on 3. The remaining 6 of 9 tracked benchmarks cannot be compared: 3 have a result for only one of the two models, 3 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 3 of 9 tracked benchmarks for both models — Claude 3 Opus leads on 3.

Benchmark	Claude 3 Opus	GPT-4 (Mar 2023)	Leads
Epoch Capabilities Index (ECI)	126.9	125.9	Claude 3 Opus
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.472	0.357	Claude 3 Opus
MATH Level 5	0.375	Not measured	Comparison unavailable — GPT-4 (Mar 2023) has no published result
OTIS Mock AIME 2024-2025	0.047	0.006	Claude 3 Opus
FrontierMath	Not measured	Not measured	Not measured on both
FrontierMath Tier 4	Not measured	Not measured	Not measured on both
SimpleQA Verified	0.126	Not measured	Comparison unavailable — GPT-4 (Mar 2023) has no published result
Chess Puzzles	0.050	Not measured	Comparison unavailable — GPT-4 (Mar 2023) has no published result

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

GPT-4 (Mar 2023) has no published result on Chess Puzzles, MATH Level 5, SimpleQA Verified.
3 tracked benchmarks have 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 3 Opus	GPT-4 (Mar 2023)
Output	—	$60.00 stale

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 3 Opus → · GPT-4 (Mar 2023) → · the full AI Model Rankings table