ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Fable 5.1vsGLM-5.3-Flash

Claude Fable 5.1 leads 4 of 4 shared benchmarks. GLM-5.3-Flash is 92.3x cheaper per token. Both offer a 1M-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
4 – 0
Claude Fable 5.1 leads
Cheaper per token
GLM-5.3-Flash
92.3x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100% · —
Anthropic · Z.ai
Claude Fable 5.1
Anthropic · released 2026-09-01
textvision
Context
1M
Max out
128K
Input /1M
$10
Output /1M
$50
Cached /1M
$0.25
Scores
8 · 5 core
GLM-5.3-Flash
Z.ai · released 2026-09-16
textvision
Context
1M
Max out
131K
Input /1M
$0.15
Output /1M
$0.5
Cached /1M
$0.03
Scores
19 · 6 core
Quality

Benchmark matrix

BenchmarkClaude Fable 5.1GLM-5.3-FlashΔEdge
Reported by both · 4
FrontierMath Tier 4 v2 (Epoch AI run)87.8% epoch17.1% epoch+70.7 ptClaude Fable 5.1
FrontierMath Tiers 1-3 v2 (Epoch AI run)90.2% epoch55.8% epoch+34.4 ptClaude Fable 5.1
GDPval-AA v21853 1773 +80Claude Fable 5.1
OTIS Mock AIME 2024-2025 (Epoch AI run)100% epoch93.9% epoch+6.1 ptClaude Fable 5.1
Only Claude Fable 5.1 reports · 4
Humanity's Last Exam (no tools)60.9% not reported
CursorBench 3.2.073.4% not reported
SimpleQA Verified70.8% epochnot reported
Terminal-Bench Science 0.152.6% not reported
Only GLM-5.3-Flash reports · 15
GPQA Diamondnot reported90.2% epoch
LMArena Elonot reported1471.9
Agents' Last Exam (ALE-CLI)not reported26.3%
AutomationBench v1.0.6not reported48.8%
BabyVisionnot reported53.4%
Chartography (with tools)not reported78%
CharXiv Reasoning (with tools)not reported89.4%
DeepSWE v1.1not reported63.4%
HLE (with tools)not reported55.3%
MMVUnot reported80.5%
MVBenchnot reported77.8%
NL2Reponot reported56.3%
OfficeQA Pronot reported62.4%
Terminal-Bench 2.1not reported84.3%
Toolathlon Verifiednot reported78.4%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Fable 5.1 minus GLM-5.3-Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecClaude Fable 5.1GLM-5.3-FlashEdge
Context window1M tokens1M tokensTie
Max output128K tokens131K tokensGLM-5.3-Flash
Input price / 1M$10 $0.15 GLM-5.3-Flash
Output price / 1M$50 $0.5 GLM-5.3-Flash
Cached input / 1M$0.25 $0.03 GLM-5.3-Flash
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$60$0.65GLM-5.3-Flash
Modalitiestext · visiontext · visionTie
Released2026-09-012026-09-16
Cited benchmark scores819
Reliability

Provider status

All providers
More matchups

Claude Fable 5.1 vs …

More matchups

GLM-5.3-Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Fable 5.1 and GLM-5.3-Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.