OLMo 2 1124 7B: Complete Benchmark Performance Guide

other olmo-2-1124-7b 2024-11-24 Apache 2.0

In-depth analysis of OLMo 2 1124 7B performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versionolmo-2-1124-7b
Release Date2024-11-24
Context Window4096 tokens
Input Modalitiestext
Output Modalitiestext
LicenseApache 2.0
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 68.3 % 2024-11-24 5-shot view
HUMANEVAL 53.2 pass@1 2024-11-24 — view
GSM8K 57.2 % 2024-11-24 0-shot CoT view
MATH 39.3 % 2024-11-24 0-shot CoT view
BBH 63.1 % 2024-11-24 3-shot CoT view
GPQA 26.3 % 2024-11-24 0-shot view
IFEVAL 56 % 2024-11-24 prompt_strict view
ARC 86.2 % 2024-11-24 challenge view
MUSR 39.2 % 2024-11-24 0-shot view
WINOGRANDE 75.3 % 2024-11-24 0-shot view

Pricing

Tier Price Currency
Input$0.18 / MtokUSD
Output$0.18 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-11-24

Compliance

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

OLMo 2 1124 7B

Model Overview

AllenAI OLMo 2 1124 7B 第三代模型, 4K 上下文, 改进训练稳定性与推理能力, 完全开源。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other olmo-2-1124-7b 2024-11-24 4K text text Apache 2.0

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 68.3 % 5-shot
HumanEval 53.2 pass@1 —
GSM8K (Grade School Math 8K) 57.2 % 0-shot CoT
MATH 39.3 % 0-shot CoT
BBH (BIG-Bench Hard) 63.1 % 3-shot CoT
GPQA 26.3 % 0-shot
IFEval 56.0 % prompt_strict
ARC 86.2 % challenge
MUSR 39.2 % 0-shot
WinoGrande 75.3 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Reliable general-purpose model.

Weaknesses

  • Proprietary, not self-hostable.
  • Context window 4K is limited.

Use Cases

  • General chat and Q&A

References