Back to all LLMs

Gemini 3 Pro Preview

1M context with mandatory reasoning mode for careful analysis of retrieved content before responding. Multimodal support enables RAG across text, images, audio, and video with robust tool-calling for dynamic retrieval. If you want to compare the best LLMs for your data, try Agentset.

Leaderboard Rank
#7
of 16
ELO Rating
1509
#7
Win Rate
44.1%
#8
Latency
17904ms
#13

Model Information

Provider
Google
License
Proprietary
Input Price per 1M
$2.00
Output Price per 1M
$12.00
Context Window
1049K
Release Date
2025-11-18
Model Name
gemini-3-pro-preview
Total Evaluations
1350

Performance Record

Wins596 (44.1%)
Losses581 (43.0%)
Ties173 (12.8%)
Wins
Losses
Ties

LLMs Are Just One Piece of RAG

Agentset gives you a managed RAG pipeline with the top-ranked models and best practices baked in. No infrastructure to maintain, no LLM orchestration to manage.

Trusted by teams building production RAG applications

5M+
Documents
1,500+
Teams
99.9%
Uptime

Performance Overview

ELO ratings by dataset

Gemini 3 Pro Preview's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Gemini 3 Pro Preview - ELO by Dataset

Detailed Metrics

Dataset breakdown

Performance metrics across different benchmark datasets, including accuracy and latency percentiles.

PG

ELO 155148.4% WR218W-204L-28T

Quality Metrics

Correctness
4.90
Faithfulness
4.93
Grounding
4.93
Relevance
5.00
Completeness
4.73
Overall
4.90

Latency Distribution

Mean
25137ms
Min
13317ms
Max
62299ms

SciFact

ELO 153039.3% WR177W-184L-89T

Quality Metrics

Correctness
4.93
Faithfulness
4.97
Grounding
4.97
Relevance
4.97
Completeness
4.83
Overall
4.93

Latency Distribution

Mean
14583ms
Min
10135ms
Max
21489ms

MSMARCO

ELO 144644.7% WR201W-193L-56T

Quality Metrics

Correctness
4.83
Faithfulness
4.83
Grounding
4.83
Relevance
5.00
Completeness
4.90
Overall
4.88

Latency Distribution

Mean
13990ms
Min
7461ms
Max
26343ms

Build RAG in Minutes, Not Months

Agentset gives you a complete RAG API with top-ranked LLMs and smart retrieval built in. Upload your data, call the API, and get grounded answers from day one.

import { Agentset } from "agentset";

const agentset = new Agentset();
const ns = agentset.namespace("ns_1234");

const results = await ns.search(
  "What is multi-head attention?"
);

for (const result of results) {
  console.log(result.text);
}

Compare Models

See how it stacks up

Compare Gemini 3 Pro Preview with other top llms to understand the differences in performance, accuracy, and latency.