in the loop

Grok 4.5
#39 of 274 scored.

xAIJul 8, 2026Closed

Capabilities Index

Range 152.2–155.6

153.9

Context

Takes text, image, file

500K

Input

Per 1M tokens

$2.00

Output

Per 1M tokens

$6.00

Benchmarks

How it scores.

  • GPQA Diamond91.3%

    15th of 186

  • FrontierMath57.2%

    38th of 81

  • ARC-AGI-252.6%

    31st of 79

  • SimpleQA Verified48.3%

    29th of 77

  • Mock AIME97.8%

    24th of 176

Everything else Epoch has for it

  • DTBench94.2%
  • ARC-AGI87.2%
  • Surface Evolver Bench74.4%
  • SimpleBench64.0%
  • APEX-Agents56.2%
  • DeepSWE53.8%
  • LMCA53.2%
  • WeirdML46.4%
  • FrontierCode42.4%
  • Chess Puzzles32.7%
  • ProofBench31.0%
  • FrontierMath-Tier-4-v2-Private24.4%
  • PostTrainBench23.4%
  • Furniture Assembly0.0%

On the index

Around it.

  1. #36Gemini 3.5 FlashGoogle · $1.50 in154.5
  2. #37Gemini 3.6 FlashGoogle · $0.75 in154.3
  3. #38Muse Spark 1.1Meta · $1.25 in154.2
  4. #39Grok 4.5xAI · $2.00 in153.9
  5. #40Qwen3.7-MaxAlibaba · $1.48 in153.7
  6. #41Grok 4.7xAI · $2.00 in153.5
  7. #42GPT-5.2OpenAI · $1.75 in153.4

Sources