Gemini 2.5 ProvsGPT-4o

Gemini 2.5 Pro
GPT-4o
Specifications
Context window
128k
API pricing
Input price
$1.25$2.50
Output price
$10.00$10.00
Cached input price
$0.125$1.25
Cheapest input
$2.50Azure
Cheapest output
$10.00Azure
Benchmarks
BullshitBench v2
20%12%
GPQA Diamond
86.4%49.9%
Benchmarks
SWE-Bench Verified
59.6%
MMMU
68%
Overview
CompanyGoogleOpenAI
Release dateMar 25 2025May 13 2024
AccessProprietaryProprietary

Other comparisons

Gemini 2.5 ProvsClaude Opus 5GPT-4ovsClaude Opus 5Gemini 2.5 ProvsMuse GlimmerGPT-4ovsMuse GlimmerGemini 2.5 ProvsGrok 4.6GPT-4ovsGrok 4.6Gemini 2.5 ProvsDeepSeek-V4-Pro-0813GPT-4ovsDeepSeek-V4-Pro-0813Gemini 2.5 ProvsMistral Medium 3.5GPT-4ovsMistral Medium 3.5Gemini 2.5 ProvsKimi K3GPT-4ovsKimi K3

Frequently asked questions

Gemini 2.5 Pro leads GPT-4o on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Gemini 2.5 Pro is cheaper on input: $1.25 vs $2.50 per million tokens. Both charge $10.00 per million output tokens. Figures are base-tier rates. GPT-4o shipped 316 days before Gemini 2.5 Pro, 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 BullshitBench v2, Gemini 2.5 Pro leads at 20% vs GPT-4o at 12%. On GPQA Diamond, Gemini 2.5 Pro leads at 86.4% vs GPT-4o at 49.9%.

Gemini 2.5 Pro was released by Google on Mar 25 2025.

GPT-4o was released by OpenAI on May 13 2024.

Gemini 2.5 Pro leads on GPQA Diamond — Gemini 2.5 Pro 86.4% vs GPT-4o 49.9%.

Gemini 2.5 Pro is cheaper on input: $1.25 vs $2.50 per million tokens. Both charge $10.00 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.