Summarise · 3 checks · max 400 tokens · benched 2026-09-16

Mistral Large 3 2512 vs Mistral Medium 3.5 vs Mistral Small 4 vs Ministral 3 8B 2512 on meeting notes to exactly three bullets

Mistral AI models side by side on "Meeting notes to exactly three bullets": Mistral Large 3 2512 scores 10/10; Ministral 3 8B 2512 is the cheapest answer scoring 8+ at $0.03 per 1,000 runs. Outputs, checks, judge reasons, latency and cost.

The prompt every model received

System

You are a concise assistant. Output only what is asked for.

User

Turn these meeting notes into exactly three bullet points. Each bullet starts with "- " and is at most 20 words. Output nothing except the three bullets.

Notes: Launch of the new billing page moves from 18 Sept to 25 Sept because the tax calculation for EU customers still fails for VAT-exempt businesses. Priya owns the fix and will demo it Thursday. Marketing will hold the announcement email until the fix is verified. Separately, the team agreed to drop support for the legacy CSV export in Q1 next year and to notify affected customers in November.

Rubric for the judge: Three bullets that capture the delayed launch, the VAT fix owner, and the CSV export decision; nothing extra.

Side by side

Every cell is one OpenRouter call at temperature 0 with the prompt's token cap and reasoning effort "low" where the model supports it. Cost is usage × the catalogue rate in models.json. Quality is one judge call to anthropic/claude-haiku-4.5 against the prompt's rubric, cached per prompt version.

Mistral Large 3 2512

mistralai/mistral-large-2512

10/10

top judge score

Latency: 483ms
Cost: $0.00015
Per 1,000: $0.15

134 in · 53 out · 41 words · checks 3/3

regex
max_words
contains

- New billing page launch delayed to 25 Sept due to EU VAT-exempt tax calculation issue.
- Priya to demo tax fix Thursday; marketing pauses announcement email until verified.
- Legacy CSV export support ends Q1; affected customers notified in November.

Judge: Three bullets exactly, each under 20 words, capturing all three required points (delayed launch, VAT fix owner, CSV decision) with no extra commentary.

Mistral Medium 3.5

mistralai/mistral-medium-3-5

10/10

Latency: 1.0s
Cost: $0.01201
Per 1,000: $12.01

146 in · 1572 out (1586 reasoning) · 32 words · checks 3/3

regex
max_words
contains

- Billing page launch delayed to 25 Sept for EU VAT fix
- Priya owns fix, demo Thursday; marketing holds announcement
- Drop legacy CSV export in Q1, notify customers in November

Judge: Three bullets, each under 20 words, capturing all three required points (delayed launch, VAT fix owner/demo, CSV export decision) with no extra commentary.

Mistral Small 4

mistralai/mistral-small-2603

10/10

Latency: 351ms
Cost: $0.00015
Per 1,000: $0.15

146 in · 215 out (188 reasoning) · 50 words · checks 3/3

regex
max_words
contains

- Launch of new billing page delayed to 25 Sept due to EU VAT-exempt tax calculation failure.
- Priya owns the fix and will demo it Thursday; marketing holds announcement email until verified.
- Team agreed to drop legacy CSV export support in Q1 next year, notify customers in November.

Judge: Three bullets, each under 20 words, capturing all three required points (delayed launch, VAT fix owner, CSV export decision) with no extra commentary.

Ministral 3 8B 2512

mistralai/ministral-8b-2512

9/10

cheapest scoring 8+

Latency: 277ms
Cost: $3.1e-5
Per 1,000: $0.03

134 in · 72 out · 47 words · checks 3/3

regex
max_words
contains

- **Billing page launch delayed to 25 Sept** due to unresolved EU VAT-exempt tax calculation issue; Priya owns fix.

- **Marketing to hold announcement email** until tax fix is verified and demoed Thursday.

- **Legacy CSV export support dropped** in Q1 2025; affected customers notified in November.

Judge: Three bullets capturing all required points within 20-word limit, but bold formatting adds unnecessary styling when task asked for bare output.

Frequently asked

What does this prompt test?

Summarise: Three bullets that capture the delayed launch, the VAT fix owner, and the CSV export decision; nothing extra. The deterministic checks are regex, max_words, contains.

Which model should I pick for this task?

If the judge's bar of 8/10 is good enough for you, Ministral 3 8B 2512 at $0.03 per 1,000 runs. If you need the top score, Mistral Large 3 2512 at $0.15 per 1,000 runs.

Same prompt, other families

Run it yourself

Re-run this prompt on Mistral AI with your own OpenRouter key, or tweak the wording and see what changes.

Side by side

Mistral Large 3 2512

Mistral Medium 3.5

Mistral Small 4

Ministral 3 8B 2512

Frequently asked

Same prompt, other families

Stop overpaying for AI tools