Gemini 2.5 Pro vs Kimi K3 (Low)
Which is better for the money: Gemini 2.5 Pro by Google or Kimi K3 (Low) by Kimi? 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
Kimi K3 (Low) scores 14.0 points higher (30.1 vs 16.1) but costs 1.4× as much to run the benchmark ($1190 vs $823; both premium class). Pick Kimi K3 (Low) when the extra intelligence is worth the premium, otherwise Gemini 2.5 Pro.
| Metric | Gemini 2.5 Pro | Kimi K3 (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 16.1 | 30.1 | +87.0% Kimi K3 (Low) is 87.0% more intelligent |
| Total AA cost (lower is better) | $822.85 | $1,190.42 | +44.7% Kimi K3 (Low) is 44.7% more expensive |
| End-to-end time (lower is better) | 26.13s | 62.29s | +138.4% Kimi K3 (Low) is 138.4% slower |
| Price per 1M tokens (in / out) | $1.25 / $10.0 | $3.00 / $15.0 | |
| Input modalities | Text, Image, Speech, Video | Text, Image |
Kimi K3 (Low) vs Gemini 2.5 Pro: 87.0% more intelligence, 44.7% more cost to run the AA benchmark, and 138.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Gemini 2.5 Pro is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 51.00 for $662.
- Kimi K3 (Low) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Gemini 2.5 ProKimi K3 (Low)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/gemini-2-5-pro/kimi-k3-low · Markdown: /api/v1/compare/gemini-2-5-pro/kimi-k3-low?format=md · llms.txt · agent skill