GPT-6 Astra (Low) vs Mistral Large 4 (Medium)
Which is better for the money: GPT-6 Astra (Low) by OpenAI or Mistral Large 4 (Medium) by Mistral? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-30.
Trade-off
Verdict
Depends on your budget
GPT-6 Astra (Low) scores 19.9 points higher (43.0 vs 23.1) but costs 1.8× as much to run the benchmark ($1651 vs $936; both premium class). Pick GPT-6 Astra (Low) when the extra intelligence is worth the premium, otherwise Mistral Large 4 (Medium).
| Metric | GPT-6 Astra (Low) | Mistral Large 4 (Medium) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.0 | 23.1 | −46.3% Mistral Large 4 (Medi… is 46.3% less intelligent |
| Total AA cost (lower is better) | $1,650.75 | $936.36 | −43.3% Mistral Large 4 (Medi… is 43.3% cheaper |
| End-to-end time (lower is better) | 10.46s | Not reported | — not comparable |
| Price per 1M tokens (in / out) | $10.0 / $50.0 | $0.70 / $2.10 | |
| Input modalities | Text, Image | Text, Image |
Mistral Large 4 (Medium) vs GPT-6 Astra (Low): 46.3% less intelligence, 43.3% less cost to run the AA benchmark, and end-to-end time not fully reported.
Today's Pareto frontier
Against the frontier
- GPT-6 Astra (Low) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 54.50 for $1124.
- Mistral Large 4 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Xhigh) scores 52.30 for $718.
GPT-6 Astra (Low)Mistral Large 4 (Medium)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-6-astra-low/mistral-large-4-medium · Markdown: /api/v1/compare/gpt-6-astra-low/mistral-large-4-medium?format=md · llms.txt · agent skill