AI model matchup

Inkling-2-Small vs Claude Fable 5

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

Inkling-2-SmallvsClaude Fable 5

Claude Fable 5 leads the RankLLMs Index by 0.2 points (62.0 vs 61.8). Verified API Pricing: .30 (Inkling-2-Small) vs $10.00 (Claude Fable 5) per 1M tokens.

Capability profile

Inkling-2-SmallClaude Fable 5

Speed duel

tps
Inkling-2-Small75
Claude Fable 5110

Price duel

$/1M
Inkling-2-Small.30
Claude Fable 5$10.00

Shorter bar = cheaper. Blended per 1M tokens.

MetricInkling-2-SmallClaude Fable 5
RankLLMs Overall Score61.8 pts 62.0 pts ▲
Reasoning93.5 ▲67.5
Coding88.0 ▲84.5
Agentic Tool Use82.5 86.0 ▲
Code Arena Elo2150 ▲1932
Inference Speed75 tps 110 tps ▲
API Price (per 1M tokens).30 ▲$10.00
Context Window1M 1M
LicenseApache-2.0 Proprietary
Global Rank#12 #11 ▲

Decision notes

What the numbers suggest

Claude Fable 5 leads the RankLLMs overall score by 0.2 points. Inkling-2-Small has the lower listed API rate (.30 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 Fable 5 leads
61.8 to 62.0 pts
Coding score
Inkling-2-Small leads
88.0 to 84.5 pts
Reasoning score
Inkling-2-Small leads
93.5 to 67.5 pts
Agentic score
Claude Fable 5 leads
82.5 to 86.0 pts

Choose by workload

Which profile fits your use?

Thinking Machines Lab

Consider Inkling-2-Small when

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

View Inkling-2-Small profile

Anthropic

Consider Claude Fable 5 when

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

View Claude Fable 5 profile

Compare a different pairRead editorial comparisons