Skip to content

Gemini 3 Pro Preview

ModelActive
by Google · family “gemini-pro-preview”
Epoch Capabilities Index
Not scored by Epoch AI
Released
18 Nov 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (21)

BenchmarkDomainScorevs best recordedSettingRunSource
CL-benchlong-context15.8%
57%
——External ↗
ProofBenchmath20.0%
20%
——External ↗
Chess Puzzlesgames31.0% ±4.6
43%
—8 Dec 2025Eval log ↗
Remote Labor Indexagents1.3%
6%
——External ↗
GDPvalagents40.3%
81%
——External ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath18.8% ±5.7
39%
—21 Nov 2025Epoch ↗
GSO-Benchcoding18.6%
40%
——External ↗
Terminal Benchagents69.4% ±2.1
82%
agent: Ante18 Nov 2025External ↗
ARC-AGI-2reasoning31.1%
33%
——External ↗
METR Time Horizonsagents71.0%
83%
——External ↗
GeoBenchmultimodal84.0%
95%
——External ↗
FrontierMath-2025-02-28-Privatesupersededmath37.6% ±2.8
72%
—21 Nov 2025Epoch ↗
VPCTmultimodal91.0%
100%
——External ↗
HLEknowledge37.5%
68%
——External ↗
WeirdMLcoding69.9% ±0.0
75%
——External ↗
OTIS Mock AIME 2024-2025math91.4% ±3.7
91%
—19 Nov 2025Eval log ↗
Balroggames58.1%
85%
——External ↗
SimpleBenchreasoning76.4%
93%
——External ↗
SWE-Bench verifiedcoding72.9% ±2.0
87%
—13 Feb 2026Eval log ↗
GPQA diamondscience92.6% ±1.7
97%
—19 Nov 2025Eval log ↗
ARC-AGIreasoning75.0%
76%
——External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 1h ago. Steps show when the price changed.

Events