Models / o3 Mini

OpenAI

o3 Mini

7 published results from 2 sources. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider
OpenAI
Sources
2
Our benchmarks
0
Price per million tokens
$1.10 in · $4.40 out
OpenRouter list price, 1 Oct 2026 · 200,000-token context

Reported by others

Reported by Arena (formerly LMArena)
1,328
Business, management and finance · rank 214 of 402
Unit
Arena rating, higher is better
Range
1,321 to 1,335
Sample
7659 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,301
Creative writing · rank 207 of 407
Unit
Arena rating, higher is better
Range
1,294 to 1,308
Sample
8128 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,366
Expert prompts · rank 177 of 359
Unit
Arena rating, higher is better
Range
1,355 to 1,377
Sample
2864 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,344
Instruction following · rank 194 of 409
Unit
Arena rating, higher is better
Range
1,339 to 1,349
Sample
16905 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,348
Overall · rank 203 of 409
Unit
Arena rating, higher is better
Range
1,345 to 1,352
Sample
56572 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,325
Writing, literature and language · rank 203 of 408
Unit
Arena rating, higher is better
Range
1,319 to 1,331
Sample
13365 votes
Configuration
o3 Mini
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by SimpleQA Verified (Epoch AI)
15.3%
Correct answers · rank 76 of 85
Unit
% of questions, higher is better
Configuration
o3 Mini (high)
Measured
31 Aug 2026
Not shown
Not answers grounded in your documents; tests what the model remembers.

Compare o3 Mini with