Mistral Large 3
By Mistral · released 2025-12-02 (10 months) · snapshot 2026-10-24
- Intelligence index
- 9.30
- Cost to run the AA index
- $46.4
- Price per 1M tokens (in / out)
- $0.50 / $1.50
- End-to-end time
- 7.18s
Is Mistral Large 3 on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-6 Luna (Medium) is at least as smart for the same money or less.
Next step up: GPT-6 Luna (High), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Mistral Large 3 | Mistral | 9.30 | $46.4 | 7.18s | 2025-12-02 | ||
| 2 | GPT-6 Luna (Medium) | OpenAI | 29.90 | $31.2 | 8.25s | 2026-09-22 | Frontier | |
| 3 | GPT-6 Luna (High) | OpenAI | 32.90 | $47.9 | 12.4s | 2026-09-22 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Mistral Large 3 today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: mistral-large-3.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
What the Mistral Large 3 release did to the frontier on 2025-12-02
None of its 1 effort levels reached the frontier at launch.
Closest miss: Mistral Large 3, 0.4 points below DeepSeek V3 0324 at 2.3× the cost.
Should you use Mistral Large 3?
Should you use Mistral Large 3?
Only when it fits your setup: GPT-6 Luna (Medium) is at least as smart for the same money or less, so Mistral Large 3 is off the value frontier today.
What is better and cheaper than Mistral Large 3?
GPT-6 Luna (Medium) — at least as smart for the same money or less.
How much does Mistral Large 3 cost?
$0.50/$1.50 in/out per 1M tokens, and $46.4 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Mistral Large 3 on the Pareto frontier?
No: GPT-6 Luna (Medium) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Mistral Large 3 is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/mistral-large-3 · Markdown: /api/v1/models/mistral-large-3?format=md · llms.txt · agent skill