in the loop

Grok 4.6
#21 of 274 scored.

xAIAug 12, 2026Closed

Capabilities Index

Range 154.5–159.0

156.4

Context

Takes text, image, file

500K

Input

Per 1M tokens

$2.00

Output

Per 1M tokens

$6.00

Benchmarks

How it scores.

  • GPQA Diamond92.0%

    10th of 186

  • FrontierMath66.0%

    27th of 81

  • ARC-AGI-267.1%

    20th of 79

  • SimpleQA Verified49.3%

    27th of 77

  • Mock AIME99.2%

    14th of 176

Everything else Epoch has for it

  • DTBench95.5%
  • ARC-AGI87.5%
  • SimpleBench71.1%
  • DeepSWE67.5%
  • WeirdML67.3%
  • APEX-Agents65.3%
  • LMCA57.0%
  • ProofBench51.0%
  • FrontierCode48.0%
  • Chess Puzzles36.9%
  • FrontierMath-Tier-4-v2-Private31.7%
  • EBR-bench30.5%
  • Mystery Game Puzzles27.3%
  • FrontierSWE25.3%
  • Furniture Assembly14.3%

On the index

Around it.

  1. #18GPT-5.3 CodexOpenAI · $1.75 in156.8
  2. #19Muse Spark 1.3Meta · $1.25 in156.8
  3. #20Gemini 3.8 FlashGoogle · $0.75 in156.7
  4. #21Grok 4.6xAI · $2.00 in156.4
  5. #22Qwen 3.8 MaxAlibaba156.4
  6. #23GPT-5.6 LunaOpenAI · $0.20 in156.4
  7. #24GPT-6 LunaOpenAI · $0.10 in156.3

Sources