in the loop

GPT-6 Luna
#24 of 274 scored.

OpenAISep 22, 2026Closed

Capabilities Index

Range 153.7–158.8

156.3

Context

Takes file, image, text

1.05M

Input

Per 1M tokens

$0.10

Output

Per 1M tokens

$0.50

Benchmarks

How it scores.

  • GPQA Diamond87.3%

    38th of 186

  • FrontierMath79.0%

    16th of 81

  • ARC-AGI-259.3%

    28th of 79

  • SimpleQA Verified41.4%

    41st of 77

  • Mock AIME98.9%

    16th of 176

Everything else Epoch has for it

  • ARC-AGI86.7%
  • DTBench83.5%
  • ProofBench64.0%
  • FrontierMath-Tier-4-v2-Private56.1%
  • LMCA52.3%
  • APEX-Agents44.3%
  • FrontierCode42.4%
  • Chess Puzzles27.4%
  • Furniture Assembly20.2%
  • Mystery Game Puzzles0.0%

On the index

Around it.

  1. #21Grok 4.6xAI · $2.00 in156.4
  2. #22Qwen 3.8 MaxAlibaba156.4
  3. #23GPT-5.6 LunaOpenAI · $0.20 in156.4
  4. #24GPT-6 LunaOpenAI · $0.10 in156.3
  5. #25Claude Opus 4.7Anthropic · $5.00 in156.3
  6. #26Claude Sonnet 5Anthropic · $2.00 in156.2
  7. #27GLM-5.3Z.ai · $0.039 in155.6

Sources