Claude 4.5 Haiku (Reasoning) vs Kimi K2.7 Code
Which is better for the money: Claude 4.5 Haiku (Reasoning) by Anthropic or Kimi K2.7 Code by Kimi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-08-07.
Trade-off
Verdict
Depends on your budget
Kimi K2.7 Code scores 13.1 points higher (43.0 vs 29.9) but costs 1.2× as much to run the benchmark ($545 vs $471; premium vs mid-range cost classes). Pick Kimi K2.7 Code when the extra intelligence is worth the premium, otherwise Claude 4.5 Haiku (Reasoning).
| Metric | Claude 4.5 Haiku (Reasoning) | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 29.9 | 43.0 | +43.8% Kimi K2.7 Code is 43.8% more intelligent |
| Total AA cost (lower is better) | $471.22 | $544.58 | +15.6% Kimi K2.7 Code is 15.6% more expensive |
| End-to-end time (lower is better) | 17.02s | 66.82s | +292.6% Kimi K2.7 Code is 292.6% slower |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.95 / $4.00 | |
| Input modalities | Not reported | Not reported |
Kimi K2.7 Code vs Claude 4.5 Haiku (Reasoning): 43.8% more intelligence, 15.6% more cost to run the AA benchmark, and 292.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude 4.5 Haiku (Reasoning) is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
- Kimi K2.7 Code is off the frontier: at the same or lower cost, GPT-5.6 Luna (max) scores 52.30 for $172.
Claude 4.5 Haiku (Reasoning)Kimi K2.7 CodeToday'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-4-5-haiku-reasoning/kimi-k2-7-code · Markdown: /api/v1/compare/claude-4-5-haiku-reasoning/kimi-k2-7-code?format=md · llms.txt · agent skill