GLM-5.2 vs Claude Fable 5.1

Head-to-head technical comparison of intelligence, capabilities, and API pricing.

GLM-5.2
Z.ai
AI Mastery Index91.5
LMSYS Arena1465
Technical (MMLU-Pro)91.2%
Cost per 1M Tokens$1.4
Claude Fable 5.1
Anthropic
AI Mastery Index96.9
LMSYS Arena1504
Technical (MMLU-Pro)95.9%
Cost per 1M Tokens$10

Which should you use?

Claude Fable 5.1 leads on the composite index by 5.4 points (91.5 vs 96.9).

Cost is the sharper difference: Claude Fable 5.1 is 7.1x the input price of GLM-5.2 ($10 against $1.4 per 1M), so at volume the choice is usually decided by budget rather than benchmarks.

Only GLM-5.2 ships open weights, which decides it outright if the workload has to run on your own hardware.

Pick GLM-5.2 when

  • Cheaper input tokens — $1.4 against $10 per 1M, so Claude Fable 5.1 costs 7.1x as much to feed.
  • Open weights, so it is the only one of the two you can run on your own hardware or keep data entirely in-house.
  • Better value per point of measured capability: $0.015 per index point against $0.103.

Pick Claude Fable 5.1 when

  • Higher composite index — 96.9 against 91.5, a gap of 5.4 points.
  • Ahead on Arena Elo by 39 points (1504 vs 1465), which is outside the board's published confidence intervals.
  • Stronger on MMLU-Pro: 95.9% against 91.2%.

Value per point of measured capability, at list input pricing: GLM-5.2 $0.015 · Claude Fable 5.1 $0.103 per index point. Run your own token mix through the token cost calculator — a comparison at list price ignores caching and batch discounts, which move real bills more than this gap does.

Our reporting on Z.ai and Anthropic