Back to all LLMs

Gemini 2.5 Pro

1M token context window accommodates extensive retrieved document sets without chunking. Multimodal RAG processes up to 3,000 images, 60 minutes of video, and 8.4 hours of audio alongside text.

Leaderboard Rank
#8
of 11
ELO Rating
1400
#8
Win Rate
32.3%
#8
Latency
15199ms
#7

Model Information

Provider
Google
License
Proprietary
Input Price per 1M
$1.25
Output Price per 1M
$10.00
Context Window
1049K
Release Date
2025-06-17
Model Name
gemini-2.5-pro
Total Evaluations
900

Performance Record

Wins291 (32.3%)
Losses479 (53.2%)
Ties130 (14.4%)
Wins
Losses
Ties

Performance Overview

ELO ratings by dataset

Gemini 2.5 Pro's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.

Gemini 2.5 Pro - ELO by Dataset

Detailed Metrics

Dataset breakdown

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

MSMARCO

ELO 145242.3% WR127W-126L-47T

Quality Metrics

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

Latency Distribution

Mean
12449ms
Min
7629ms
Max
23066ms

PG

ELO 144036.7% WR110W-174L-16T

Quality Metrics

Correctness
5.00
Faithfulness
5.00
Grounding
5.00
Relevance
5.00
Completeness
5.00
Overall
5.00

Latency Distribution

Mean
17834ms
Min
11067ms
Max
49308ms

SciFact

ELO 130818.0% WR54W-179L-67T

Quality Metrics

Correctness
4.80
Faithfulness
4.83
Grounding
4.80
Relevance
4.77
Completeness
4.63
Overall
4.77

Latency Distribution

Mean
15314ms
Min
8817ms
Max
35365ms

Compare Models

See how it stacks up

Compare Gemini 2.5 Pro with other top llms to understand the differences in performance, accuracy, and latency.