Key Specifications

SpecificationGemini 1.5 ProGemini 2.0 Flash
Vendorgooglegoogle
Version1.5-pro2.0-flash
Release Date2024-02-152024-12-11
Context Window2e+06 tokens1.048576e+06 tokens
Input Modalitiestext, image, audio, videotext, image, audio, video
Output Modalitiestexttext
LicenseProprietaryProprietary
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkGemini 1.5 ProGemini 2.0 FlashWinner
ARC95.7Gemini 2.0 Flash
BBH8483.4Gemini 1.5 Pro
GPQA55Gemini 2.0 Flash
GSM8K91.792.7Gemini 2.0 Flash
HUMANEVAL71.990.7Gemini 2.0 Flash
IFEVAL85.9Gemini 2.0 Flash
MATH58.571.3Gemini 2.0 Flash
MMLU85.986.3Gemini 2.0 Flash
MUSR69.3Gemini 2.0 Flash
WINOGRANDE89.5Gemini 2.0 Flash

Pricing Comparison

Tier (per Mtok)Gemini 1.5 ProGemini 2.0 Flash
Input$1.25$0.1
Output$5$0.4
Cache Read$0.3125$0
Cache Write$1.25$0

Gemini 1.5 Pro contre Gemini 2.0 Flash

Aperçu du modèle

Gemini 1.5 Pro and Gemini 2.0 Flash are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Spécifications clés

FournisseurDate de sortieFenêtre de contexteLicence
Google / Google2024-02-15 / 2024-12-112000K / 1048KProprietary / Proprietary

Performance aux benchmarks

BenchmarkGemini 1.5 ProGemini 2.0 FlashGagnant
ARC95.7B
BBH (BIG-Bench Hard)84.083.4A
GPQA55.0B
GSM8K (Grade School Math 8K)91.792.7B
HumanEval71.990.7B
IFEval85.9B
MATH58.571.3B
MMLU (Massive Multitask Language Understanding)85.986.3Tie
MUSR69.3B
WinoGrande89.5B

Comparaison des prix

EntréeSortieLecture cacheÉcriture cache
— / —— / —— / —— / —

par million de jetons — A / B

Forces & Faiblesses

Gemini 1.5 Pro

  • ✅ MMLU score 85.9, strong knowledge reasoning.
  • ✅ GSM8K 91.7, robust math reasoning.
  • ✅ 支持文本、图像、音频多模态输入。
  • ✅ 上下文窗口 2000K,支持长文本。
  • ⚠️ 闭源专有模型,不支持自托管。

Gemini 2.0 Flash

  • ✅ MMLU score 86.3, strong knowledge reasoning.
  • ✅ HumanEval 90.7, excellent code generation.
  • ✅ GSM8K 92.7, robust math reasoning.
  • ✅ 支持文本、图像、音频多模态输入。
  • ⚠️ 闭源专有模型,不支持自托管。

Avis de la rédaction

Gemini 1.5 Pro and Gemini 2.0 Flash each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

FAQ

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

Références

Editor's Take

See Editor's Take section.