in the loop

GPT-5.4 Nano
#82 of 274 scored.

OpenAIMar 17, 2026Closed

Capabilities Index

Range 143.5–147.6

145.8

Context

Takes file, image, text

400K

Input

Per 1M tokens

$0.20

Output

Per 1M tokens

$1.25

Benchmarks

How it scores.

  • GPQA Diamond71.3%

    85th of 186

  • FrontierMath44.9%

    50th of 81

  • ARC-AGI-25.7%

    50th of 79

  • SimpleQA Verified11.7%

    73rd of 77

  • Mock AIME87.8%

    60th of 176

Everything else Epoch has for it

  • DTBench67.1%
  • ARC-AGI51.5%
  • WeirdML49.2%
  • LMCA43.4%
  • Chess Puzzles26.4%
  • FrontierMath-Tier-4-v2-Private12.2%
  • ProofBench5.0%
  • Mystery Game Puzzles0.0%

On the index

Around it.

  1. #79Kimi K2 ThinkingMoonshot · $0.60 in146.0
  2. #80MiniMax-M2.7MiniMax · $0.21 in145.8
  3. #81GLM-5Z.ai · $0.60 in145.8
  4. #82GPT-5.4 NanoOpenAI · $0.20 in145.8
  5. #83o4-miniOpenAI · $1.10 in145.6
  6. #84GPT-5 miniOpenAI · $0.25 in145.5
  7. #85Gemini 2.5 Pro (Jun 2025)Google145.3

Sources