AI model matchup

Claude Fable 5.2 vs Claude Mythos 5.2

A side-by-side look at published capability scores, listed API pricing, speed, context, and license - to help you decide which trade-offs fit your work.

OpenAI

GPT-5.6 Sol

Rank #1 • Score 57.2
Comparison Metrics
Speed: 89c/s vs 68c/s
Pricing: $7.78 vs $7.22
Anthropic

Claude Opus 5

Rank #2 • Score 56.2

Claude Fable 5.2vsClaude Mythos 5.2

Claude Mythos 5.2 leads the RankLLMs Index by 1.3 points (70.8 vs 69.5). Verified API Pricing: .00 (Claude Fable 5.2) vs .00 (Claude Mythos 5.2) per 1M tokens.

Capability profile

Claude Fable 5.2Claude Mythos 5.2

Speed duel

tps
Claude Fable 5.285
Claude Mythos 5.280

Price duel

$/1M
Claude Fable 5.2.00
Claude Mythos 5.2.00

Shorter bar = cheaper. Blended per 1M tokens.

MetricClaude Fable 5.2Claude Mythos 5.2
RankLLMs Overall Score69.5 pts 70.8 pts ▲
Reasoning95.8 96.5 ▲
Coding92.4 93.0 ▲
Agentic Tool Use94.0 94.8 ▲
Code Arena Elo2280 2320 ▲
Inference Speed85 tps ▲80 tps
API Price (per 1M tokens).00 .00
Context Window1M 1M
LicenseProprietary Proprietary
Global Rank#3 #2 ▲

Decision notes

What the numbers suggest

Claude Mythos 5.2 leads the RankLLMs overall score by 1.3 points. Claude Fable 5.2 has the lower listed API rate (.00 per 1M tokens).

Treat the overall index as a starting point, then prioritize the benchmark that resembles your task. Published scores and provider pricing can change; this comparison does not represent a first-party test of either model.

Overall index
Claude Mythos 5.2 leads
69.5 to 70.8 pts
Coding score
Claude Mythos 5.2 leads
92.4 to 93.0 pts
Reasoning score
Claude Mythos 5.2 leads
95.8 to 96.5 pts
Agentic score
Claude Mythos 5.2 leads
94.0 to 94.8 pts

Choose by workload

Which profile fits your use?

Anthropic

Consider Claude Fable 5.2 when

your workload gives more weight to the lower listed API rate. Compare those signals with your own task mix, latency needs, and budget.

View Claude Fable 5.2 profile

Anthropic

Consider Claude Mythos 5.2 when

your workload gives more weight to the higher listed coding score, the higher listed reasoning score, the higher overall index score. Compare those signals with your own task mix, latency needs, and budget.

View Claude Mythos 5.2 profile

Compare a different pairRead editorial comparisons