Inference
EN
Google

Gemini 1.5 Flash

Gemini 1.5 Flash is a standard model from Google. 10 benchmarks count toward its index, in 4 categories.

  • Closed weights
  • Standard
  • Input: text
  • Released 2024-05
RankedEnough results for an index.
IndexAll categories, out of 100.20.2±9.6Median 51.0
CoverageIndex weight that has results.55%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.1 counted8.3—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.2 counted21.683 / 84
KnowledgeFacts and expert knowledge.3 counted22.3262 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.4 counted18.0161 / 168

Results

10 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math43.5% ±1.155 / 88
GPQA diamond · Epoch AIKnowledge43.8% ±2.4167 / 217
OTIS Mock AIME 2024-2025Math10.1% ±4.1154 / 200
Massive Multi-discipline Multimodal UnderstandingMultimodal58.3%24 / 28
Graduate-Level Google-Proof Q&AKnowledge50.0%125 / 141
Artificial Analysis GPQA DiamondKnowledge46.3%181 / 199
Artificial Analysis MMMU-ProMultimodal48.4%103 / 113
Measuring Short-Form Factuality in Large Language ModelsKnowledge8.6%13 / 14
Artificial Analysis Humanity's Last ExamKnowledge3.2%217 / 222
FrontierMath-2025-02-28-PrivateMath0.0%68 / 69
American Invitational Mathematics Examination 2025Math14.7%53 / 53
Software Engineering Benchmark VerifiedCoding9.6%114 / 114
FrontierMath-2025-02-28-PublicMath0.0%33 / 64

Sources

BenchLMCC BY-NC 4.0Epoch AICC BY

History

5 releases
Index21.0 → 20.2
23 Oct 202612 Nov 2026

Questions

How good is Gemini 1.5 Flash?
Its index is 20.2 out of 100. That is place 278 of 283 ranked models.
What is Gemini 1.5 Flash best at?
Math: 18.0 out of 100, place 161 of 168.
What is the context window of Gemini 1.5 Flash?
1M tokens.
Is Gemini 1.5 Flash open source?
No. Its weights are not published.
When was Gemini 1.5 Flash released?
May 2024.

Badge

Gemini 1.5 Flash on Inference360: place 278 of 283, index 20.2
HTML
<a href="https://inference360.ai/models/gemini-1-5-flash"><img src="https://inference360.ai/badges/gemini-1-5-flash.svg" alt="Gemini 1.5 Flash on Inference360: place 278 of 283, index 20.2" height="20"></a>
Markdown
[![Gemini 1.5 Flash on Inference360: place 278 of 283, index 20.2](https://inference360.ai/badges/gemini-1-5-flash.svg)](https://inference360.ai/models/gemini-1-5-flash)

Compare with

Gemma 4 E2B21.9Claude 3 Haiku22.0Llama 3.1 8B17.9Granite-4.0-H-1B16.3Gemini 2.0 Flash29.5

More from Google

All models
Gemma 2 27BUnrankedGemini 1.5 ProUnrankedGemini 1.0 ProUnrankedGemini 2.0 Flash29.5Gemini 2.0 Flash-LiteUnranked