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 2.5 Flash Preview (Sep '25) (Reasoning)

Gemini 2.5 Flash Preview (Sep '25) (Reasoning) is a Google Gemini 2.5 model, part of the Gemini generation that emphasized thinking, long-context work, multimodal reasoning, and developer access through AI Studio and Vertex AI. The profile lets you compare the specific Pro, Flash, or Flash-Lite variant on measured quality, speed, and cost.

Gemini 2.5 thinking models

Operational Metrics

Output Speedn/a
First Tokenn/a
Blended Price-

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseSep 25, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: MMLU-Pro

Rank #41 across 345 models.

84.2%

Strength: LCB

Rank #63 across 343 models.

71.3%

Strength: SciCode

Rank #87 across 472 models.

40.5%

Strength Profile

Percentile score by analysis domain.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall31.1#136
Artificial Analysis Coding Indexcoding24.6#153
Artificial Analysis Math Indexmath78.3#71
MMLU-Proreasoning84.2%#41
GPQA
reasoning
79.3%
#106
Humanity's Last Examreasoning12.7%#115
LiveCodeBenchcoding71.3%#63
SciCodecoding, reasoning40.5%#87