Claude Haiku 5.5 (Max) vs Inkling Small
Which is better for the money: Claude Haiku 5.5 (Max) by Anthropic or Inkling Small by Thinking Machines? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
Claude Haiku 5.5 (Max) scores 17.7 points higher (43.4 vs 25.7) but costs 1.4× as much to run the benchmark ($330 vs $241; both mid-range class). Pick Claude Haiku 5.5 (Max) when the extra intelligence is worth the premium, otherwise Inkling Small.
| Metric | Claude Haiku 5.5 (Max) | Inkling Small | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 25.7 | −40.8% Inkling Small is 40.8% less intelligent |
| Total AA cost (lower is better) | $330.25 | $240.85 | −27.1% Inkling Small is 27.1% cheaper |
| End-to-end time (lower is better) | 324.30s | 12.95s | −96.0% Inkling Small is 96.0% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Speech |
Inkling Small vs Claude Haiku 5.5 (Max): 40.8% less intelligence, 27.1% less cost to run the AA benchmark, and 96.0% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- Inkling Small is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Claude Haiku 5.5 (Max)Inkling SmallToday's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-haiku-5-5/inkling-small · Markdown: /api/v1/compare/claude-haiku-5-5/inkling-small?format=md · llms.txt · agent skill