in the loop

GPT-4 (Mar 2023)
#181 of 274 scored.

OpenAIMar 14, 2023Closed

Capabilities Index

Range 119.3–130.4

125.9

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond14.3%

    165th of 186

  • Mock AIME0.5%

    172nd of 176

Everything else Epoch has for it

  • HellaSwag93.7%
  • GSM8K92.0%
  • MMLU81.9%
  • Winogrande75.0%
  • METR Time Horizons36.1%

On the index

Around it.

  1. #178GPT-4o miniOpenAI · $0.15 in126.6
  2. #179GPT-4 Turbo (Nov 2023)OpenAI126.5
  3. #180Llama 3.1-70BMeta125.9
  4. #181GPT-4 (Mar 2023)OpenAI125.9
  5. #182Llama 3.2 90BMeta125.5
  6. #183Qwen2-72BAlibaba125.3
  7. #184DeepSeek-V2 (MoE-236B, May 2024)DeepSeek124.8

Sources