in the loop

GPT-5.5 Instant
#101 of 274 scored.

OpenAIMay 5, 2026Closed

Capabilities Index

Range 139.8–145.3

142.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond76.7%

    74th of 186

  • FrontierMath26.3%

    63rd of 81

  • Mock AIME68.0%

    96th of 176

Everything else Epoch has for it

  • Chess Puzzles7.4%
  • FrontierMath-Tier-4-v2-Private2.4%

On the index

Around it.

  1. #98Gemini 2.5 Flash (Sep 2025)Google143.0
  2. #99Gemma 4 31B ITGoogle · $0.09 in142.7
  3. #100Claude Opus 4Anthropic142.7
  4. #101GPT-5.5 InstantOpenAI142.5
  5. #102Qwen3.5-35B-A3BAlibaba · $0.08 in142.5
  6. #103Gemini 2.5 Pro (May 2025)Google142.5
  7. #104Claude Haiku 4.5Anthropic · $1.00 in142.4

Sources