NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemini 2.0 Flash Lite
Google DeepMind logo

Gemini 2.0 Flash Lite

by Google DeepMind · Released Feb 2025

Multimodal1M Context
45.3
avg score
Rank #170
Compare
Better than 46% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.07
Output $/1M
$0.30
Type
multimodal
License
Proprietary
Benchmarks
5 tested
Data as of
About

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maintaining quality on par with larger models like Gemini Pro 1.5,...

Tested on 5 benchmarks · BenchGecko score 45.3. Top scores: HELM — IFEval (82.4%), HELM — WildBench (79.0%), HELM — MMLU-Pro (72.0%).

Looking for similar performance at lower cost?
gpt-oss-20b scores 45.0 (99% as good) at $0.02/1M input · 76% cheaper
Capabilities
reasoning
79.0
#18 globally
math
37.4
#164 globally
knowledge
61.0
#52 globally
language
82.4
#50 globally
Benchmark Scores
Compare All
Tested on 5 benchmarks · Ranked across 4 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

79.0·
mathCompare math →
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

37.4·
knowledgeCompare knowledge →
HELM — MMLU-Pro

Stanford HELM evaluation of MMLU-Pro. Tests broad knowledge with increased difficulty.

72.0·
HELM — GPQA

Stanford HELM evaluation of GPQA. Tests graduate-level scientific reasoning.

50.0·
Quick compare:OpenAI logovs gpt-oss-20bAlibaba Qwen logovs Qwen3.8 27BNVIDIA logovs Nemotron 3 Ultra
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Google DeepMind Gemini 2.0 Flash
Feb 2025
44.4
$0.10/M in1.0Mctx20 benchmarks
Jan 2024
44.1-0.3
n/an/actx20 benchmarks
Feb 2025
45.3+1.2
$0.07/M in1.0Mctx5 benchmarks
Jan 2024
33.0-12.3
n/an/actx7 benchmarks
See the full Gemini 2.0 Flash family →
Similar Models
OpenAI logo
gpt-oss-20b
OpenAI
45.0$0.02/1M
Alibaba Qwen logo
Qwen3.8 27B
Alibaba Qwen
45.6$0.42/1M
NVIDIA logo
Nemotron 3 Ultra
NVIDIA
45.6$0.50/1M
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
BenchGecko API
gemini-2-0-flash-lite-001
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedFeb 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.000
Available On
Google DeepMind logoGoogle DeepMind$0.07
Categories
reasoningmathknowledgelanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
OpenAI logogpt-oss-20b
45.0
Alibaba Qwen logoQwen3.8 27B
45.6
NVIDIA logoNemotron 3 Ultra
45.6
Alibaba Qwen logoQwen3 235B A22B Instruct 2507
44.9
Gemini 2.0 Flash Lite is a proprietary multimodal AI model by Google DeepMind, released in February 2025. It has an average benchmark score of 45.3. Context window: 1M tokens.

Related Models

gpt-oss-20b · OpenAIQwen3.8 27B · Alibaba QwenNemotron 3 Ultra · NVIDIAQwen3 235B A22B Instruct 2507 · Alibaba QwenQwen3.7 Flash · Alibaba Qwen

Benchmarks

HELM — IFEvalHELM — WildBenchHELM — MMLU-ProHELM — GPQAHELM — Omni-MATH

Related Pages

Google DeepMind · ProviderGoogle DeepMind · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-05-03

  • Gemini 2.0 Flash Lite by Google DeepMind. BenchGecko score 45.3, rank 170 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.0750 input · $0.30 output per 1M tokens (as of 2026-05-03).

How to cite · data as of 2026-05-03

Gemini 2.0 Flash Lite · benchmarks, pricing and providers. BenchGecko, data as of 2026-05-03. https://benchgecko.ai/model/gemini-2-0-flash-lite-001

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP