EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Google

Gemini 3 Pro Preview (high)

Gemini 3 Pro Preview (high) is a Google Gemini 3 family model, from the generation Google introduced for stronger reasoning, multimodal understanding, coding, and agentic product experiences. This profile focuses on the exact preview or reasoning variant captured in the local benchmark snapshot.

Introducing Gemini 3

Operational Metrics

Output Speed128.7 tok/s
First Token20.79s
Blended Price$4.50/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseNov 18, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: MMLU-Pro

Rank #1 across 345 models.

89.8%

Strength: LCB

Rank #1 across 343 models.

91.7%

Strength: SciCode

Rank #3 across 472 models.

56.1%

Watch Area: TTFT

Rank #274 across 293 models.

20.79s

Watch Area: Blended $

Rank #274 across 325 models.

$4.50/M

Watch Area: Output $

Rank #274 across 325 models.

$12.00/M

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall48.4#30
Artificial Analysis Coding Indexcoding46.5#21
Artificial Analysis Math Indexmath95.7#7
MMLU-Proreasoning89.8%#1
GPQA
reasoning
90.8%
#11
Humanity's Last Examreasoning37.2%#9
LiveCodeBenchcoding91.7%#1
SciCodecoding, reasoning56.1%#3
Output Speedspeed128.7 tok/s#83
Time to First Tokenspeed20.79s#274
Blended Pricecost$4.50/M#274
Input Pricecost$2.00/M#261
Output Pricecost$12.00/M#274
Value Indexcost, overall10.8#239