Celeris-1 vs DeepSeek V4 Pro 0813 (Reasoning, Max Effort)
Which is better for the money: Celeris-1 by Celeris or DeepSeek V4 Pro 0813 (Reasoning, Max Effort) by DeepSeek? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-09-09.
Trade-off
Verdict
Depends on your budget
DeepSeek V4 Pro 0813 (Reasoning, Max Ef… scores 30.0 points higher (36.3 vs 6.3) but costs 19× as much to run the benchmark ($1122 vs $60.0; premium vs mid-range cost classes). They are not alternatives at one budget: pick DeepSeek V4 Pro 0813 (Reasoning, Max Ef… when you need intelligence above 6.3, and Celeris-1 when 6.3 is enough.
| Metric | Celeris-1 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 6.3 | 36.3 | +476.2% DeepSeek V4 Pro 0813 … is 5.8× more intelligent |
| Total AA cost (lower is better) | $59.99 | $1,122.27 | +1770.8% DeepSeek V4 Pro 0813 … is 19× more expensive |
| End-to-end time (lower is better) | 0.97s | 32.92s | +3293.8% DeepSeek V4 Pro 0813 … is 3293.8% slower |
| Price per 1M tokens (in / out) | $0.20 / $0.70 | $1.32 / $3.96 | |
| Input modalities | Not reported | Not reported |
DeepSeek V4 Pro 0813 (Reasoning, Max Effort) vs Celeris-1: 476.2% more intelligence, 1770.8% more cost to run the AA benchmark, and 3293.8% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Celeris-1 is off the frontier: at the same or lower cost, MiMo-V2.5 scores 22.30 for $42.6.
- DeepSeek V4 Pro 0813 (max) is off the frontier: at the same or lower cost, GLM-5.3-Flash scores 41.90 for $280.
Celeris-1DeepSeek V4 Pro 0813 (Reasoning, Max Effort)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/deepseek-v4-pro · Markdown: /api/v1/compare/celeris-1/deepseek-v4-pro?format=md · llms.txt · agent skill