Claude Opus 5.5vsGemini 2.5 Pro

Claude Opus 5.5
Gemini 2.5 Pro
Specifications
Context window
1M
API pricing
Input price
$4.00$1.25
Output price
$20.00$10.00
Cached input price
$0.20$0.125
Cheapest input
$0.625Google AI Studio
Cheapest output
$5.00Google AI Studio
Benchmarks
Humanity's Last Exam · with tools
67.7%18.8%
Benchmarks
BullshitBench v2
20%
SWE-Bench Verified
59.6%
FrontierCode v1.1 (Main) · main split
54.4%
Terminal-Bench 4.0
66.4%
Terminal-Bench-Science 0.1
58.7%
GPQA Diamond
86.4%
OSWorld 2.0
81.8%
AutomationBench
40%
GDPval-AA v2.1
1846
Chartography · with tools
89%
MMMU
68%
Overview
CompanyAnthropicGoogle
Release dateSep 22 2026Mar 25 2025
AccessProprietaryProprietary

Other comparisons

Claude Opus 5.5vsGPT-6 AstraGemini 2.5 ProvsGPT-6 AstraClaude Opus 5.5vsMuse Spark 1.3Gemini 2.5 ProvsMuse Spark 1.3Claude Opus 5.5vsGrok 4.7Gemini 2.5 ProvsGrok 4.7Claude Opus 5.5vsDeepSeek-V4.1-FlashGemini 2.5 ProvsDeepSeek-V4.1-FlashClaude Opus 5.5vsMistral Medium 3.5Gemini 2.5 ProvsMistral Medium 3.5Claude Opus 5.5vsKimi K3Gemini 2.5 ProvsKimi K3

Frequently asked questions

Claude Opus 5.5 leads Gemini 2.5 Pro on 1 of the 1 benchmark they both report (Humanity's Last Exam). Gemini 2.5 Pro is cheaper on both input and output: $1.25 vs $4.00 per million input tokens, and $10.00 vs $20.00 per million output tokens. Figures are base-tier rates. Gemini 2.5 Pro shipped 546 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 Gemini 2.5 Pro at 18.8%.