in the loop

GLM-5.3
#27 of 274 scored.

Z.aiAug 14, 2026Closed

Capabilities Index

Range 153.6–157.9

155.6

Context

Takes text

1.05M

Input

Per 1M tokens

$0.039

Output

Per 1M tokens

$6.00

Benchmarks

How it scores.

  • GPQA Diamond87.9%

    30th of 186

  • FrontierMath68.8%

    24th of 81

  • SimpleQA Verified41.0%

    43rd of 77

  • Mock AIME91.1%

    49th of 176

Everything else Epoch has for it

  • DTBench79.5%
  • WeirdML75.4%
  • DeepSWE69.0%
  • LMCA65.3%
  • APEX-Agents56.6%
  • ProofBench49.0%
  • FrontierCode40.1%
  • FrontierSWE30.2%
  • FrontierMath-Tier-4-v2-Private29.3%
  • Mystery Game Puzzles26.2%
  • Chess Puzzles16.9%

On the index

Around it.

  1. #24GPT-6 LunaOpenAI · $0.10 in156.3
  2. #25Claude Opus 4.7Anthropic · $5.00 in156.3
  3. #26Claude Sonnet 5Anthropic · $2.00 in156.2
  4. #27GLM-5.3Z.ai · $0.039 in155.6
  5. #28GPT-5.2 ProOpenAI · $21 in155.4
  6. #29DeepSeek V4 Pro 0813DeepSeek · $0.66 in155.3
  7. #30Claude Opus 4.6Anthropic · $5.00 in155.2

Sources