in the loop

GPT-5.5 Pro
#8 of 274 scored.

OpenAIApr 23, 2026Closed

Capabilities Index

Range 159.0–165.8

162.1

Context

Takes file, image, text

1.05M

Input

Per 1M tokens

$30

Output

Per 1M tokens

$180

Benchmarks

How it scores.

  • GPQA Diamond91.9%

    12th of 186

  • FrontierMath87.7%

    8th of 81

  • ARC-AGI-284.6%

    10th of 79

  • Mock AIME100%

    1st of 176

Everything else Epoch has for it

  • ARC-AGI96.5%
  • DTBench93.3%
  • FrontierMath-Tier-4-v2-Private78.0%
  • SimpleBench72.3%
  • LMCA63.5%
  • Chess Puzzles62.1%

On the index

Around it.

  1. #5Claude Fable 5.1Anthropic · $10 in164.7
  2. #6Claude Opus 5Anthropic · $5.00 in162.8
  3. #7GPT-6 SolOpenAI · $2.00 in162.7
  4. #8GPT-5.5 ProOpenAI · $30 in162.1
  5. #9Claude Fable 5Anthropic · $10 in162.1
  6. #10GPT-5.6 SolOpenAI · $2.00 in161.7
  7. #11GPT-5.6 TerraOpenAI · $2.00 in159.6

Sources