Gemini 3 Flash

Gemini 3 Flash is a standard model from Google. 21 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Standard
  • Input: text
  • Released 2025-12
RankedEnough results for an index.
IndexAll categories, out of 100.55.0±4.0Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.198/sMedian 67/s
First tokenSeconds to the first output token.0.9 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.50Median $0.60
Output / 1MUS dollars per 1M output tokens.$3.00Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.1466±4 #37Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.4 counted48.5141 / 218
CodingCode writing and repair.1 counted56.8—
ReasoningLogic problems and puzzles.4 counted50.8109 / 227
MultimodalTasks with images and text.2 counted67.316 / 84
KnowledgeFacts and expert knowledge.4 counted60.761 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted40.5—
MathMath problems.5 counted57.356 / 168

Results

21 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
ParseBench: document parsing for AI agents (LlamaIndex leaderboard)MultimodalAbove fitFar above this model's index.74.1%4 / 39
τ²-bench AirlineAgentic82.5%3 / 22
SimpleQA VerifiedKnowledgeAbove fitFar above this model's index.66.8% ±1.513 / 91
OTIS Mock AIME 2024-2025Math95.6% ±3.140 / 200
FrontierMath-2025-02-28-PrivateMath35.6% ±2.814 / 69
GPQA diamond · Epoch AIKnowledge89.4% ±2.247 / 217
Artificial Analysis MMMU-ProMultimodal78.6%33 / 113
Chess PuzzlesReasoning40.0% ±4.936 / 90
SWE-Bench verified · Epoch AICoding75.4% ±2.013 / 32
τ²-bench TelecomAgentic91.2%8 / 18
Artificial Analysis GPQA DiamondKnowledge81.2%95 / 199
Artificial Analysis IFBenchInstruction55.1%72 / 146
Critical Physics TasksReasoning1.4%113 / 214
Mystery Game PuzzlesReasoning20.0% ±4.045 / 80
τ²-bench BankingAgentic27.3%16 / 28
FrontierMath-Tiers-1-3-v2-PrivateMath51.2% ±3.054 / 90
τ²-bench RetailAgentic76.8%14 / 23
FrontierMath-Tier-4-v2-PrivateMath17.1% ±5.952 / 72
Claw-EvalAgentic49.2%38 / 42
JobBenchAgentic11.4%33 / 36
FrontierMath-2025-02-28-PublicMath60.0% ±16.311 / 64

Sources

BenchLMCC BY-NC 4.0Epoch AICC BYSierra ResearchMITSWE-bench teamNo licence stated

History

5 releases
Index56.0 → 55.0
23 Oct 202612 Nov 2026
Output / 1M$3.00 → $3.00
23 Oct 202612 Nov 2026

Questions

How much does Gemini 3 Flash cost?
$0.50 per 1M input tokens, $3.00 per 1M output tokens.
How good is Gemini 3 Flash?
Its index is 55.0 out of 100. That is place 103 of 283 ranked models.
What is Gemini 3 Flash best at?
Multimodal: 67.3 out of 100, place 16 of 84.
How fast is Gemini 3 Flash?
198 output tokens per second, 0.9 s to the first token.
What is the context window of Gemini 3 Flash?
1M tokens.
Is Gemini 3 Flash open source?
No. Its weights are not published.
When was Gemini 3 Flash released?
December 2025.

Badge

Gemini 3 Flash on Inference360: place 103 of 283, index 55.0
HTML
<a href="https://inference360.ai/models/gemini-3-flash"><img src="https://inference360.ai/badges/gemini-3-flash.svg" alt="Gemini 3 Flash on Inference360: place 103 of 283, index 55.0" height="20"></a>
Markdown
[![Gemini 3 Flash on Inference360: place 103 of 283, index 55.0](https://inference360.ai/badges/gemini-3-flash.svg)](https://inference360.ai/models/gemini-3-flash)

Compare with

GPT-555.0Inkling-Small55.1Inkling54.8Gemini 3 Pro57.9

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from Google

All models
Nano Banana Pro (Gemini 3 Pro Image Preview)UnrankedGemini 2.5 Flash Native Audio Preview (12-2025)UnrankedGemini 3 Pro57.9Gemini 3 Flash Preview57.5Nano Banana (Gemini 2.5 Flash Image)Unranked