Gemini 1.5 Flash: Complete Benchmark Performance Guide

google 1.5-flash 2024-05-14 Proprietary

In-depth analysis of Gemini 1.5 Flash performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorgoogle
Version1.5-flash
Release Date2024-05-14
Context Window1e+06 tokens
Input Modalitiestext, image, audio, video
Output Modalitiestext
LicenseProprietary
Documentationhttps://ai.google.dev/gemini-api/docs

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 76 % 2024-05-14 5-shot view
HUMANEVAL 67.5 pass@1 2024-05-14 — view
GSM8K 75.2 % 2024-05-14 0-shot CoT view
MATH 53.2 % 2024-05-14 0-shot CoT view
BBH 71.7 % 2024-05-14 3-shot CoT view
GPQA 38.5 % 2024-05-14 0-shot view
IFEVAL 68 % 2024-05-14 prompt_strict view
ARC 93.4 % 2024-05-14 challenge view
MUSR 46.1 % 2024-05-14 0-shot view
WINOGRANDE 78.9 % 2024-05-14 0-shot view

Pricing

Tier Price Currency
Input$0.075 / MtokUSD
Output$0.3 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://ai.google.dev/pricing · as of 2024-05-14

Compliance

  • Data Residency: US
  • SOC2: ✓
  • HIPAA: ✗
  • GDPR: ✓
  • ISO 27001: ✓

Gemini 1.5 Flash

Model Overview

Google Gemini 1.5 Flash 经济型模型, 1M 上下文, 速度快成本低, 适合大规模多模态任务。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Google 1.5-flash 2024-05-14 1000K text, image, audio, video text Proprietary

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 76.0 % 5-shot
HumanEval 67.5 pass@1 —
GSM8K (Grade School Math 8K) 75.2 % 0-shot CoT
MATH 53.2 % 0-shot CoT
BBH (BIG-Bench Hard) 71.7 % 3-shot CoT
GPQA 38.5 % 0-shot
IFEval 68.0 % prompt_strict
ARC 93.4 % challenge
MUSR 46.1 % 0-shot
WinoGrande 78.9 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Input Modalities: text, image, audio.
  • Context window 1000K.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Long document summarization
  • Vision and image understanding

References