Inference
EN
Google

Gemini 3 Flash Preview

Gemini 3 Flash Preview is a model from Google. 14 benchmarks count toward its index, in 6 categories.

  • Input: text · image · file · audio · video
  • Released 2025-12
RankedEnough results for an index.
IndexAll categories, out of 100.57.5±5.3Median 51.0
CoverageIndex weight that has results.90%
SpeedOutput tokens per second.78/sMedian 67/s
First tokenSeconds to the first output token.1.3 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.50batch $0.25Median $0.60
Output / 1MUS dollars per 1M output tokens.$3.00batch $1.50 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
google/gemini-3-flash-preview
Max outputMaximum output tokens per request.
66K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.05
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
3 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DatabricksCloud$0.50$3.001.05M
Google Vertex AIMaker$0.50$3.001.05M
OpenRouterRouter$0.50$3.001.05M

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted57.387 / 218
CodingCode writing and repair.5 counted55.098 / 209
ReasoningLogic problems and puzzles.2 counted60.365 / 227
MultimodalTasks with images and text.1 counted69.2—
KnowledgeFacts and expert knowledge.2 counted57.081 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted57.3—

Results

14 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
SWE-bench Verified · SWE-bench/experimentsCoding75.8%3 / 65
Terminal-Bench 1.0Agentic60.0% ±5.53 / 47
AIMEMath95.6% ±0.58 / 95
MMLU ProKnowledge88.6% ±0.318 / 135
MMMU ProMultimodal87.6% ±0.813 / 92
LiveCodeBenchCoding85.6% ±1.029 / 142
IOI v1Coding39.1% ±10.513 / 61
Terminal-Bench 2.0 · Vals AIAgentic51.7% ±5.318 / 66
GPQA Diamond · Vals AIKnowledge87.9% ±1.637 / 135
ARC-AGI-1 (semi-private)Reasoning84.7%51 / 126
ARC-AGI-2 (semi-private)Reasoning33.6%55 / 131
SWE-benchCoding75.0% ±1.944 / 87
Terminal-Bench 2.1 · Vals AIAgentic53.9% ±1.353 / 75
Vibe Code Bench v1.1Coding20.2% ±3.990 / 123
Code MigrationCoding6.4% ±1.169 / 77
MedCodeHealthcare55.9% ±2.15 / 106
LegalBenchLegal86.9% ±0.411 / 149
MortgageTaxFinance68.7% ±0.911 / 97
MedQAHealthcare95.8% ±0.211 / 95
MGSMMultilingual93.3% ±1.510 / 74
CorpFin v2Finance66.4% ±0.919 / 131
TaxEval v2Finance73.9% ±0.945 / 143
ARC-AGI-2 (public eval)Reasoning34.0%49 / 122
ARC-AGI-1 (public eval)Reasoning88.3%48 / 116
ProgramBenchCoding0.0%34 / 65
CaseLaw v2Legal55.8% ±0.132 / 53
Finance Agent v1.1Finance47.6% ±2.831 / 51
Legal Research BenchLegal18.3% ±2.768 / 90
Finance Agent (v2)Finance42.6% ±0.460 / 79
Tax Agent BenchFinance11.8% ±2.364 / 82
MedScribeHealthcare69.9% ±1.995 / 109
EMBFinance26.0% ±2.967 / 75

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedARC Prize FoundationTerms restrict reuseSWE-bench teamNo licence statedmodels.devMIT

History

5 releases
Index58.7 → 57.5
23 Oct 202612 Nov 2026
Output / 1M$3.00 → $3.00
23 Oct 202612 Nov 2026

Questions

How much does Gemini 3 Flash Preview cost?
$0.50 per 1M input tokens, $3.00 per 1M output tokens.
How good is Gemini 3 Flash Preview?
Its index is 57.5 out of 100. That is place 89 of 283 ranked models.
What is Gemini 3 Flash Preview best at?
Reasoning: 60.3 out of 100, place 65 of 227.
How fast is Gemini 3 Flash Preview?
78 output tokens per second, 1.3 s to the first token.
What is the context window of Gemini 3 Flash Preview?
1.05M tokens.
When was Gemini 3 Flash Preview released?
December 2025.

Badge

Gemini 3 Flash Preview on Inference360: place 89 of 283, index 57.5
HTML
<a href="https://inference360.ai/models/google-gemini-3-flash-preview"><img src="https://inference360.ai/badges/google-gemini-3-flash-preview.svg" alt="Gemini 3 Flash Preview on Inference360: place 89 of 283, index 57.5" height="20"></a>
Markdown
[![Gemini 3 Flash Preview on Inference360: place 89 of 283, index 57.5](https://inference360.ai/badges/google-gemini-3-flash-preview.svg)](https://inference360.ai/models/google-gemini-3-flash-preview)

Compare with

DeepSeek V4 Pro 042357.6Qwen3.7 Plus57.7Qwen 3.6 Max (preview)57.2

Lower price

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

More from Google

All models
Gemini 2.5 Flash Native Audio Preview (12-2025)UnrankedGemini 3 Flash55.0Nano Banana Pro (Gemini 3 Pro Image Preview)UnrankedGemini 3 Pro57.9Gemini 3 Pro Deep ThinkUnranked