Comparing 2 models

Claude Fable 5.2 vs GLM 5.2

Benchmarks through

Verdict

Claude Fable 5.2 and GLM 5.2 are not yet ranked on the same task, so compare the specifications below. GLM 5.2 costs 1142.9x less per input token. GLM 5.2 accepts 1.0x more context. Only GLM 5.2 has open weights for self-hosting.

  • Choose GLM 5.2 for you need to self-host.

Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.

metric
Model 1Claude Fable 5.2
Model 2GLM 5.2
Best for
Agentic Coding (#1)
Best Cheap LLM for High Volume (#1)
Provider
anthropic
z-ai
Context
1M
1.0MBest
Input / 1M
$8
$0.007Best
Output / 1M
$40
$6.80Best
Tool use
yesBest
yesBest
Vision
yesBest
—
Reasoning
yesBest
yesBest
Open-weight
—
yesBest
Released
Nov 9, 2026
Jun 13, 2026

Measured head to head

Benchmarks both models were run on

EvaluationClaude Fable 5.2GLM 5.2Source
Design Arena Coding1375 Elo1276 Elosource · 2026-11-15
Design Arena Full-stack Agent1400 Elo1215 Elosource · 2026-11-15
Design Arena UI1382 Elo1286 Elosource · 2026-11-15
Design Arena Website1352 Elo1277 Elosource · 2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)95.1% ± 1.359.2% ± 3source · 2026-11-06
GPQA Diamond (Epoch AI)93.9% ± 1.691.9% ± 1.6source · 2026-11-06
LMArena Agent30.40.2source · 2026-11-11
LMArena Agent Steerability33-1source · 2026-11-11
LMArena Agent Task Outcome221.7source · 2026-11-11
LMArena Agent Tool Hallucination11source · 2026-11-11
LMArena WebDev1838 Elo1608 Elosource · 2026-11-11
OTIS Mock AIME (Epoch AI)99.7% ± 0.386.4% ± 4.2source · 2026-11-06
SimpleQA Verified (Epoch AI)94% ± 0.834.2% ± 1.5source · 2026-11-06

Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.