Claude Haiku 5.5 (Medium) vs Kimi K3 (Max)
Which is better for the money: Claude Haiku 5.5 (Medium) by Anthropic or Kimi K3 (Max) by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
Kimi K3 (Max) scores 9.1 points higher (43.6 vs 34.5) but costs 65× as much to run the benchmark ($3658 vs $56.4; flagship vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K3 (Max) when you need intelligence above 34.5, and Claude Haiku 5.5 (Medium) when 34.5 is enough.
| Metric | Claude Haiku 5.5 (Medium) | Kimi K3 (Max) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.5 | 43.6 | +26.4% Kimi K3 (Max) is 26.4% more intelligent |
| Total AA cost (lower is better) | $56.36 | $3,658.07 | +6390.5% Kimi K3 (Max) is 65× more expensive |
| End-to-end time (lower is better) | 10.41s | 63.08s | +506.0% Kimi K3 (Max) is 506.0% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $3.00 / $15.0 | |
| Input modalities | Text, Image | Text, Image |
Kimi K3 (Max) vs Claude Haiku 5.5 (Medium): 26.4% more intelligence, 6390.5% more cost to run the AA benchmark, and 506.0% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Medium) is on today's frontier: nothing is both smarter and cheaper.
- Kimi K3 (Max) is off the frontier: at the same or lower cost, Kimi K3.1 Pro scores 55.10 for $3117.
Claude Haiku 5.5 (Medium)Kimi K3 (Max)Today'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-medium/kimi-k3 · Markdown: /api/v1/compare/claude-haiku-5-5-medium/kimi-k3?format=md · llms.txt · agent skill