Mistral Small 4 (Reasoning)
By Mistral · released 2026-03-16 (4 months) · snapshot 2026-08-07
- Intelligence index
- 19.70
- Cost to run the AA index
- $87.7
- Price per 1M tokens (in / out)
- $0.15 / $0.60
- End-to-end time
- 18.4s
Is Mistral Small 4 (Reasoning) on the Pareto frontier, and what beats it?
Off the frontier
No. DeepSeek V4 Flash 0731 (Reasoning, Max Effort) is at least as smart for the same money or less.
Next step up: GPT-5.6 Luna (max), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Mistral Small 4 (Reasoning) | Mistral | 19.70 | $87.7 | 18.4s | 2026-03-16 | ||
| 2 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 51.80 | $72.0 | 24.9s | 2026-07-31 | Frontier | |
| 3 | GPT-5.6 Luna (max) | OpenAI | 52.30 | $172 | 106.4s | 2026-07-09 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Mistral Small 4 (Reasoning) today
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: mistral-small-4.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
What the Mistral Small 4 release did to the frontier on 2026-03-16
1 of 2 effort levels reached the frontier at launch (Mistral Small 4 (Reasoning)). Impact 0.11, #36 of 41 releases this past year.
Should you use Mistral Small 4 (Reasoning)?
Should you use Mistral Small 4 (Reasoning)?
Only when it fits your setup: DeepSeek V4 Flash 0731 (Reasoning, Max Effort) is at least as smart for the same money or less, so Mistral Small 4 (Reasoning) is off the value frontier today.
What is better and cheaper than Mistral Small 4 (Reasoning)?
DeepSeek V4 Flash 0731 (Reasoning, Max Effort) — at least as smart for the same money or less.
How much does Mistral Small 4 (Reasoning) cost?
$0.15/$0.60 in/out per 1M tokens, and $87.7 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Mistral Small 4 (Reasoning) on the Pareto frontier?
No: DeepSeek V4 Flash 0731 (Reasoning, Max Effort) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Mistral Small 4 (Reasoning) 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-small-4 · Markdown: /api/v1/models/mistral-small-4?format=md · llms.txt · agent skill