// head_to_head

Claude Fable 5 vs GLM 5.3 Flash

Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

Claude Fable 5 scores higher, GLM 5.3 Flash costs less — it depends on your workload.

Claude Fable 5 is ahead by 11.4 points overall, and GLM 5.3 Flash lists 168× cheaper per blended million tokens. Whether 11.4 points is worth that depends on how much a wrong answer costs you. GLM 5.3 Flash also leads on measured cost per point of capability, at $0.0161 per point.

anthropic

Claude Fable 5

Blended / 1M
$20.00
Context
1M
Released
Jun 9, 2026
Overall score
83.0
reasoningtool callingimage inputfile inputprompt caching

z-ai

GLM 5.3 Flash

Blended / 1M
$0.119
Context
1.3M
Released
Aug 26, 2026
Overall score
71.6
reasoningtool callingimage inputvideo inputprompt caching

Specs and pricing

MetricClaude Fable 5GLM 5.3 Flash
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

83.0win71.6
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.7925$0.0161win
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$20.00$0.119win
Input price / 1M$10.00$0.075win
Output price / 1M$50.00$0.250win
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$1.00$0.015win
Context window1M1.3Mwin
Max output tokens128K131K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Claude Fable 5 on top, GLM 5.3 Flash below, both out of 100.

Agentic coding
62.2
56.8
Coding
86.0
79.0
Reasoning
89.7
77.6
Mathematics
96.0
81.2
Data analysis
80.5
76.4
Language
90.7
77.3
Instruction following
75.8
52.8

What each one costs to run

Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.

WorkloadClaude Fable 5GLM 5.3 Flash
Support chatbot

1.2K in / 400 out × 200K requests

$5752.00/mo$33.68/mo
RAG assistant

8K in / 600 out × 100K requests

$7400.00/mo$51.00/mo
Coding agent

40K in / 4K out × 20K requests

$6960.00/mo$46.40/mo
Document extraction

20K in / 1.5K out × 50K requests

$13,300/mo$90.75/mo
Bulk classification

500 in / 20 out × 5M requests

$25,500/mo$182.50/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

GLM 5.3 Flash

Lowest measured cost per point of capability at $0.0161 per point — the gap compounds with every request.

Quality matters more than the bill

Claude Fable 5

Highest overall LiveBench score of the two at 83.0.

The workload is coding or agentic work

Claude Fable 5

Leads on agentic coding — 62.2 against 56.8.

You need to fit large documents in one call

GLM 5.3 Flash

Wider context window — 1.3M against 1M.

Claude Fable 5 vs GLM 5.3 Flash FAQ

Which is better, Claude Fable 5 or GLM 5.3 Flash?

Claude Fable 5 scores higher, GLM 5.3 Flash costs less — it depends on your workload. Claude Fable 5 is ahead by 11.4 points overall, and GLM 5.3 Flash lists 168× cheaper per blended million tokens. Whether 11.4 points is worth that depends on how much a wrong answer costs you. GLM 5.3 Flash also leads on measured cost per point of capability, at $0.0161 per point.

Is Claude Fable 5 cheaper than GLM 5.3 Flash?

GLM 5.3 Flash is cheaper. On a 3:1 input:output blend, Claude Fable 5 lists at $20.00 per million tokens and GLM 5.3 Flash at $0.119 — GLM 5.3 Flash is 168× cheaper. Input and output are priced separately — Claude Fable 5 charges $10.00 in and $50.00 out, GLM 5.3 Flash charges $0.075 and $0.250 — so the model that looks cheaper flips depending on how output-heavy your workload is.

Claude Fable 5 vs GLM 5.3 Flash: which scores higher on benchmarks?

Claude Fable 5 scores 83.0 and GLM 5.3 Flash scores 71.6 overall on LiveBench, the mean of its seven categories. That is a 11.4-point lead for Claude Fable 5. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.

Which gives better value for money, Claude Fable 5 or GLM 5.3 Flash?

GLM 5.3 Flash. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. Claude Fable 5 works out at $0.7925 per point and GLM 5.3 Flash at $0.0161.

Does Claude Fable 5 or GLM 5.3 Flash have a bigger context window?

GLM 5.3 Flash has the larger context window: 1M for Claude Fable 5 against 1.3M for GLM 5.3 Flash. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.

Do Claude Fable 5 and GLM 5.3 Flash support prompt caching?

Both publish a cached-input rate: $1.00 per million for Claude Fable 5 and $0.015 for GLM 5.3 Flash, against full input rates of $10.00 and $0.075. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.

Related comparisons

How these numbers are produced

  • Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • ScoresLiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
  • “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.