in the loop

Grok 4.20
#46 of 274 scored.

xAIFeb 17, 2026Closed

Capabilities Index

Range 149.4–154.5

152.0

Context

Takes text, image, file

2M

Input

Per 1M tokens

$1.25

Output

Per 1M tokens

$2.50

Benchmarks

How it scores.

  • GPQA Diamond85.8%

    44th of 186

  • FrontierMath44.9%

    50th of 81

  • ARC-AGI-265.1%

    21st of 79

  • SimpleQA Verified30.2%

    60th of 77

  • Mock AIME92.2%

    45th of 176

  • Terminal-Bench57.3%

    11th of 35

Everything else Epoch has for it

  • ARC-AGI89.5%
  • DTBench83.5%
  • WeirdML52.3%
  • LMCA45.5%
  • CL-bench22.2%
  • Chess Puzzles20.0%
  • FrontierMath-Tier-4-v2-Private17.1%
  • ProofBench14.0%
  • CL-bench Life11.9%

On the index

Around it.

  1. #43Gemini 3 ProGoogle152.9
  2. #44Claude Sonnet 4.6Anthropic · $3.00 in152.2
  3. #45Muse SparkMeta152.0
  4. #46Grok 4.20xAI · $1.25 in152.0
  5. #47GLM-5.3-FlashZ.ai · $0.15 in151.9
  6. #48Gemini 3 FlashGoogle151.8
  7. #49GLM-5.2Z.ai · $0.06 in151.8

Sources