in the loop

GPT-6.1 Sol
#3 of 274 scored.

OpenAISep 29, 2026Closed

Capabilities Index

Range 162.9–170.6

166.1

Context

Takes file, image, text

1.05M

Input

Per 1M tokens

$2.00

Output

Per 1M tokens

$10

Benchmarks

How it scores.

  • GPQA Diamond93.9%

    3rd of 186

  • FrontierMath93.7%

    1st of 81

  • ARC-AGI-294.2%

    2nd of 79

  • SimpleQA Verified73.9%

    2nd of 77

  • Mock AIME100%

    1st of 176

Everything else Epoch has for it

  • FrontierMath-Tier-4-v2-Private100%
  • ProofBench99.0%
  • ARC-AGI98.5%
  • Mystery Game Puzzles78.0%
  • Furniture Assembly71.4%
  • APEX-Agents60.0%
  • Chess Puzzles59.0%
  • EBR-bench54.3%
  • FrontierCode50.2%

On the index

Around it.

  1. #1Claude Opus 5.5Anthropic · $4.00 in167.3
  2. #2GPT-6 AstraOpenAI · $10 in166.4
  3. #3GPT-6.1 SolOpenAI · $2.00 in166.1
  4. #4Claude Sonnet 5.5Anthropic · $2.00 in165.0
  5. #5Claude Fable 5.1Anthropic · $10 in164.7
  6. #6Claude Opus 5Anthropic · $5.00 in162.8

Sources