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 Flash Preview (Reasoning)

Gemini 3 Flash Preview (Reasoning) 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 Speed193.2 tok/s
First Token5.61s
Blended Price$1.13/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseDec 17, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: LCB

Rank #2 across 343 models.

90.8%

Strength: Math

Rank #3 across 269 models.

97.0

Strength: MMLU-Pro

Rank #4 across 345 models.

89.0%

Watch Area: TTFT

Rank #244 across 293 models.

5.61s

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 Indexoverall46.4#38
Artificial Analysis Coding Indexcoding42.6#37
Artificial Analysis Math Indexmath97.0#3
MMLU-Proreasoning89.0%#4
GPQA
reasoning
89.8%
#15
Humanity's Last Examreasoning34.7%#14
LiveCodeBenchcoding90.8%#2
SciCodecoding, reasoning50.6%#15
Output Speedspeed193.2 tok/s#28
Time to First Tokenspeed5.61s#244
Blended Pricecost$1.13/M#184
Input Pricecost$0.500/M#164
Output Pricecost$3.00/M#194
Value Indexcost, overall41.2#112