in the loop

Gemini 3.7 Flash
#16 of 274 scored.

GoogleAug 13, 2026Closed

Capabilities Index

Range 155.4–159.9

157.3

Context

Takes text, image, video, file, audio

1.05M

Input

Per 1M tokens

$0.75

Output

Per 1M tokens

$3.75

Benchmarks

How it scores.

  • GPQA Diamond93.1%

    5th of 186

  • FrontierMath71.6%

    22nd of 81

  • ARC-AGI-284.6%

    10th of 79

  • SimpleQA Verified69.2%

    9th of 77

  • Mock AIME97.2%

    26th of 176

Everything else Epoch has for it

  • ARC-AGI95.5%
  • DTBench94.7%
  • APEX-Agents67.8%
  • DeepSWE65.5%
  • LMCA59.3%
  • ProofBench58.0%
  • Chess Puzzles44.2%
  • FrontierCode43.6%
  • FrontierMath-Tier-4-v2-Private36.6%
  • Mystery Game Puzzles30.6%
  • FrontierSWE20.3%
  • Remote Labor Index5.0%
  • Furniture Assembly0.0%

On the index

Around it.

  1. #13GPT-5.4 ProOpenAI · $30 in158.9
  2. #14Claude Opus 4.8Anthropic · $5.00 in158.2
  3. #15Kimi K3Moonshot · $0.80 in157.4
  4. #16Gemini 3.7 FlashGoogle · $0.75 in157.3
  5. #17GPT-5.4OpenAI · $2.50 in156.8
  6. #18GPT-5.3 CodexOpenAI · $1.75 in156.8
  7. #19Muse Spark 1.3Meta · $1.25 in156.8

Sources