ModelsCompareBest forBenchmarksStatusPricingAPI

Gemini 3.1 Flash-Lite

Google·Operational·Released 2026-03-03textvisionaudio
Context1,048.576k
Max output65.536k
Input / 1M$0.25 ↗
Output / 1M$1.5 ↗
Cached in$0.025
Benchmarks10

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tiers 1-3 v2 (Epoch AI run)#45/5927.7% ↗
GPQA Diamond (Epoch AI run)#53/7781.8% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#53/7680% ↗
GPQA Diamond#30/7086.9% ↗
Humanity's Last Exam (no tools)#23/2916% ↗
LiveCodeBench#3/972% ↗
MMMLU#4/488.9% ↗
MMMU-Pro#5/776.8% ↗
MRCR v2 (128k average)60.1% ↗
SimpleQA Verified#2/343.3% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Google

Gemini 3.8 FlashGemini 3.1 Pro PreviewGemini 3.5 Flash-LiteGemma 4 31BGemma 4 26B A4BGemma 4 12B Unified

Access Gemini 3.1 Flash-Lite and every other model through one endpoint with automatic failover: Respan gateway.