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

MiniMax M3 vs MiniMax M2.7 vs MiniMax M2.5 on meeting notes to exactly three bullets

Minimax models side by side on "Meeting notes to exactly three bullets": MiniMax M3 scores 10/10; MiniMax M2.7 is the cheapest answer scoring 8+ at $0.40 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.

MiniMax M3

minimax/minimax-m3

10/10

top judge score

Latency: 713ms
Cost: $0.00072
Per 1,000: $0.72

295 in · 522 out (392 reasoning) · 57 words · checks 3/3

regex
max_words
contains

- Billing page launch delayed from 18 Sept to 25 Sept due to EU VAT calculation bug for VAT-exempt businesses.
- Priya owns the fix and will demo it Thursday; marketing will hold the announcement email until verified.
- Team agreed to drop legacy CSV export support in Q1 next year and notify affected customers in November.

Judge: All three bullets capture the required information (delayed launch, VAT fix owner, CSV export decision), each is under 20 words, properly formatted with '- ', and no extra commentary is included.

MiniMax M2.7

minimax/minimax-m2.7

9/10

cheapest scoring 8+

Latency: 1.3s
Cost: $0.00040
Per 1,000: $0.40

139 in · 296 out (241 reasoning) · 45 words · checks 2/3

regex
max_words
contains



- New billing page launch delayed to Sept 25 due to EU tax calculation issue; Priya fixing, demo Thursday.
- Marketing to hold announcement email until tax fix is verified.
- Legacy CSV export being dropped in Q1 next year; affected customers notified in November.

Judge: Three well-formatted bullets capturing all key points (delayed launch, VAT fix owner/demo, CSV decision) within word limits; minor: first bullet slightly dense but acceptable.

MiniMax M2.5

minimax/minimax-m2.5

9/10

Latency: 1.3s
Cost: $0.00053
Per 1,000: $0.54

141 in · 460 out (348 reasoning) · 46 words · checks 2/3

regex
max_words
contains

- Billing page launch moved to Sept 25 due to EU VAT tax calculation issue; Priya will demo fix Thursday.
- Team agreed to drop legacy CSV export support in Q1 next year.
- Affected customers will be notified about the CSV export change in November.

Judge: All three bullets capture required points (delayed launch, VAT fix owner, CSV decision) within 20-word limit with no extra commentary, though first bullet could be slightly more concise.

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, MiniMax M2.7 at $0.40 per 1,000 runs. If you need the top score, MiniMax M3 at $0.72 per 1,000 runs.

Same prompt, other families

Run it yourself

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