gpt-oss-120b (High) vs Kimi K3 (Low)
Which is better for the money: gpt-oss-120b (High) by OpenAI 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 18.5 points higher (30.1 vs 11.6) but costs 9.7× as much to run the benchmark ($1190 vs $123; premium vs mid-range cost classes). They are not alternatives at one budget: pick Kimi K3 (Low) when you need intelligence above 11.6, and gpt-oss-120b (High) when 11.6 is enough.
| Metric | gpt-oss-120b (High) | Kimi K3 (Low) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 11.6 | 30.1 | +159.5% Kimi K3 (Low) is 2.6× more intelligent |
| Total AA cost (lower is better) | $122.71 | $1,190.42 | +870.1% Kimi K3 (Low) is 9.7× more expensive |
| End-to-end time (lower is better) | 11.44s | 56.42s | +393.2% Kimi K3 (Low) is 393.2% slower |
| Price per 1M tokens (in / out) | $0.15 / $0.60 | $3.00 / $15.0 | |
| Input modalities | Text | Text, Image |
Kimi K3 (Low) vs gpt-oss-120b (High): 159.5% more intelligence, 870.1% more cost to run the AA benchmark, and 393.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
- Kimi K3 (Low) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
gpt-oss-120b (High)Kimi 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/gpt-oss-120b/kimi-k3-low · Markdown: /api/v1/compare/gpt-oss-120b/kimi-k3-low?format=md · llms.txt · agent skill