Celeris-1 vs gpt-oss-20b (High)
Which is better for the money: Celeris-1 by Celeris or gpt-oss-20b (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick gpt-oss-20b (High)
gpt-oss-20b (High) vs Celeris-1: 42.9% more intelligence, 52.0% less cost to run the AA benchmark, and 1829.9% slower end-to-end.
| Metric | Celeris-1 | gpt-oss-20b (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 9.0 | +42.9% gpt-oss-20b (High) is 42.9% more intelligent |
| Total AA cost (lower is better) | $59.99 | $28.81 | −52.0% gpt-oss-20b (High) is 52.0% cheaper |
| End-to-end time (lower is better) | 0.87s | 16.79s | +1829.9% gpt-oss-20b (High) is 1829.9% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $0.05 / $0.22 | |
| Input modalities | Text, Image | Text |
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
Celeris-1gpt-oss-20b (High)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/celeris-1/gpt-oss-20b · Markdown: /api/v1/compare/celeris-1/gpt-oss-20b?format=md · llms.txt · agent skill