StarCoder2 7B: Complete Benchmark Performance Guide

other starcoder2-7b 2024-02-28 BigCode Open Model License

In-depth analysis of StarCoder2 7B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionstarcoder2-7b
Release Date2024-02-28
Context Window16384 tokens
Input Modalitiestext
Output Modalitiestext
LicenseBigCode Open Model License
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 67.4 % 2024-02-28 5-shot view
HUMANEVAL 74.6 pass@1 2024-02-28 — view
GSM8K 65 % 2024-02-28 0-shot CoT view
MATH 30.5 % 2024-02-28 0-shot CoT view
BBH 60 % 2024-02-28 3-shot CoT view
GPQA 33.6 % 2024-02-28 0-shot view
IFEVAL 54 % 2024-02-28 prompt_strict view
ARC 90.5 % 2024-02-28 challenge view
MUSR 38.3 % 2024-02-28 0-shot view
WINOGRANDE 73.1 % 2024-02-28 0-shot view

Pricing

Tier Price Currency
Input$0.2 / MtokUSD
Output$0.2 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-02-28

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

StarCoder2 7B

Model Overview

BigCode StarCoder2 7B 经济型代码模型, 16K 上下文, 7B 参数, 适合本地代码补全与生成。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other starcoder2-7b 2024-02-28 16K text text BigCode Open Model License

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 67.4 % 5-shot
HumanEval 74.6 pass@1 —
GSM8K (Grade School Math 8K) 65.0 % 0-shot CoT
MATH 30.5 % 0-shot CoT
BBH (BIG-Bench Hard) 60.0 % 3-shot CoT
GPQA 33.6 % 0-shot
IFEval 54.0 % prompt_strict
ARC 90.5 % challenge
MUSR 38.3 % 0-shot
WinoGrande 73.1 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 16K is limited.

Use Cases

  • Code generation and debugging

References