in the loop

Gemini 3.5 Flash
#36 of 274 scored.

GoogleMay 19, 2026Closed

Capabilities Index

Range 152.5–156.5

154.5

Context

Takes text, image, video, file, audio

1.05M

Input

Per 1M tokens

$1.50

Output

Per 1M tokens

$9.00

Benchmarks

How it scores.

  • GPQA Diamond90.4%

    19th of 186

  • SWE-bench Verified79.3%

    3rd of 32

  • FrontierMath62.8%

    33rd of 81

  • ARC-AGI-272.1%

    17th of 79

  • SimpleQA Verified66.2%

    11th of 77

  • Mock AIME95.5%

    32nd of 176

Everything else Epoch has for it

  • ARC-AGI92.5%
  • DTBench91.1%
  • SimpleBench72.0%
  • WeirdML62.6%
  • Surface Evolver Bench58.1%
  • LMCA55.5%
  • Chess Puzzles47.4%
  • DeepSWE37.4%
  • ProofBench31.0%
  • APEX-Agents27.5%
  • FrontierMath-Tier-4-v2-Private26.8%
  • Mystery Game Puzzles25.1%
  • EBR-bench4.8%

On the index

Around it.

  1. #33Muse Spark 1.2Meta · $1.25 in154.9
  2. #34Gemini 3.1 ProGoogle154.8
  3. #35DeepSeek V4 Flash 0731DeepSeek · $0.006 in154.5
  4. #36Gemini 3.5 FlashGoogle · $1.50 in154.5
  5. #37Gemini 3.6 FlashGoogle · $0.75 in154.3
  6. #38Muse Spark 1.1Meta · $1.25 in154.2
  7. #39Grok 4.5xAI · $2.00 in153.9

Sources