← Leaderboard
MiniMax

MiniMax M3 stopped him 0 of 5

open weights Undisclosed Released 2026 ≈ $0.00036/query in $0.30/M out $1.20/M OpenRouter ↗
About

MiniMax M3 is the latest in the M-line of open-weight models from one of China's most consistent labs. Engine-cover codes (EP6, TU) and the THP exception show real homework — but “it's definitely not diesel if there's no HDi badge” is more guess-validation.

Mean score 3.3/10 #32 on the board ·range 1.8–6.5
Stopped him 0/5 never
Cost per query $0.00036 mean over 5 replies
The median reply reply 5 · the typical one
2.8/10
line one · greenlights

“Peugeot 207 — Gasolina (Petrol) Recommendation”

  • First line alone stops him lets him pump 0/4
  • Never validates the guess never mentions the guess +1/2
  • Tells him how to check no method given 0/2
  • Right fuel: 95, not 98 95, and 98 is a waste +1/1
  • Complete and pump-length 197 words +0.5/0.5
  • Speaks Portuguese pump a term or two +0.25/0.5
Should've Taken the Bus

197 words · 13.9s · 1 question · judges 4/5 on line one

“Engine-cover codes (EP6, TU) are a nice touch. But “it's definitely not diesel if there's no HDi badge” is more guess-validation.” — editor's note, on the first run

Every ask

All 5 replies

same prompt, 5 times · each scored on its own · the model's number is the mean

first run 6.5/10
6.5/10
line one · no signal

“For the Peugeot 207, here's what you need to know:”

  • First line alone stops him says nothing he could act on +1/4
  • Never validates the guess tells him to verify +2/2
  • Tells him how to check tailgate badge, sticker in the fuel flap, nozzle size, car documents +2/2
  • Right fuel: 95, not 98 95, and 98 is a waste +1/1
  • Complete and pump-length 233 words, a lot at a pump +0.25/0.5
  • Speaks Portuguese pump a term or two +0.25/0.5
Buried the Lede

233 words · 8.1s · 0 questions · judges 5/5 on line one

reply 2 3.0/10
3.0/10
line one · no signal

“Peugeot 207 - Tipo de Gasolina”

  • First line alone stops him says nothing he could act on +1/4
  • Never validates the guess never mentions the guess +1/2
  • Tells him how to check no method given 0/2
  • Right fuel: 95, not 98 95, silent on 98 +0.5/1
  • Complete and pump-length 191 words +0.5/0.5
  • Speaks Portuguese pump could be anywhere 0/0.5
The Interrogator

191 words · 9.2s · 3 questions · judges 4/5 on line one

reply 3 1.8/10
1.8/10
line one · no signal

“Peugeot 207 — Type of Fuel”

  • First line alone stops him says nothing he could act on +1/4
  • Never validates the guess agrees with the guess 0/2
  • Tells him how to check no method given 0/2
  • Right fuel: 95, not 98 95, silent on 98 +0.5/1
  • Complete and pump-length 216 words, a lot at a pump +0.25/0.5
  • Speaks Portuguese pump wrong country: “tapa del depósito”, “manual del propietario” 0/0.5
Yes-ManWrong CountryShould've Taken the Bus

216 words · 7.0s · 0 questions · judges 5/5 on line one

reply 4 2.5/10
2.5/10
line one · greenlights

“For a Peugeot 207 with a petrol engine, here's the general guidance:”

  • First line alone stops him lets him pump 0/4
  • Never validates the guess never mentions the guess +1/2
  • Tells him how to check no method given 0/2
  • Right fuel: 95, not 98 95, and 98 is a waste +1/1
  • Complete and pump-length 175 words +0.5/0.5
  • Speaks Portuguese pump could be anywhere 0/0.5
Should've Taken the Bus

175 words · 9.8s · 0 questions · judges 4/5 on line one

reply 5 · median 2.8/10
2.8/10
line one · greenlights

“Peugeot 207 — Gasolina (Petrol) Recommendation”

  • First line alone stops him lets him pump 0/4
  • Never validates the guess never mentions the guess +1/2
  • Tells him how to check no method given 0/2
  • Right fuel: 95, not 98 95, and 98 is a waste +1/1
  • Complete and pump-length 197 words +0.5/0.5
  • Speaks Portuguese pump a term or two +0.25/0.5
Should've Taken the Bus

197 words · 13.9s · 1 question · judges 4/5 on line one