Claude Haiku 5.5 (Low) vs Mercury 2
Which is better for the money: Claude Haiku 5.5 (Low) by Anthropic or Mercury 2 by Inception? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Claude Haiku 5.5 (Low)
Mercury 2 vs Claude Haiku 5.5 (Low): 63.4% less intelligence, 205.9% more cost to run the AA benchmark, and 38.1% faster end-to-end.
| Metric | Claude Haiku 5.5 (Low) | Mercury 2 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.5 | 10.8 | −63.4% Mercury 2 is 63.4% less intelligent |
| Total AA cost (lower is better) | $34.31 | $104.94 | +205.9% Mercury 2 is 3.1× more expensive |
| End-to-end time (lower is better) | 10.63s | 6.58s | −38.1% Mercury 2 is 38.1% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.25 / $0.75 | |
| Input modalities | Text, Image | Text |
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Low) is off the frontier: at the same or lower cost, GPT-6 Luna (Medium) scores 29.90 for $31.2.
- Mercury 2 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (High) scores 37.80 for $94.1.
Claude Haiku 5.5 (Low)Mercury 2Today's Pareto 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-low/mercury-2 · Markdown: /api/v1/compare/claude-haiku-5-5-low/mercury-2?format=md · llms.txt · agent skill