Models / o4 Mini

OpenAI

o4 Mini

34 published results from 4 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
OpenAI
Sources
4
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Arena (formerly LMArena)
1,368
Overall · rank 156 of 177
Unit
Arena rating, higher is better
Range
1,358 to 1,378
Sample
2705 votes
Configuration
o4 Mini
Measured
25 Sep 2026
Not shown
Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Reported by Arena (formerly LMArena)
1,379
Business, management and finance · rank 160 of 402
Unit
Arena rating, higher is better
Range
1,372 to 1,387
Sample
7020 votes
Configuration
o4 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)
1,337
Creative writing · rank 164 of 407
Unit
Arena rating, higher is better
Range
1,329 to 1,345
Sample
5748 votes
Configuration
o4 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)
1,408
Expert prompts · rank 130 of 359
Unit
Arena rating, higher is better
Range
1,395 to 1,420
Sample
2301 votes
Configuration
o4 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)
1,369
Instruction following · rank 165 of 409
Unit
Arena rating, higher is better
Range
1,362 to 1,375
Sample
11808 votes
Configuration
o4 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)
1,391
Overall · rank 155 of 409
Unit
Arena rating, higher is better
Range
1,387 to 1,395
Sample
44637 votes
Configuration
o4 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)
1,354
Writing, literature and language · rank 164 of 408
Unit
Arena rating, higher is better
Range
1,348 to 1,361
Sample
9959 votes
Configuration
o4 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 Berkeley Function Calling Leaderboard (BFCL) V4
34.2%
Memory · rank 21 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not long-term personal memory in a product: sessions are BFCL's scripted ones.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
35.3%
Memory · rank 20 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not long-term personal memory in a product: sessions are BFCL's scripted ones.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
41.8%
Multi-turn tasks · rank 26 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
16.6%
Multi-turn tasks · rank 54 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
53.2%
Overall accuracy · rank 21 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
50.3%
Overall accuracy · rank 28 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
81.2%
Relevance detection · rank 41 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not whether the call itself was right; only that one was attempted.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
81.2%
Relevance detection · rank 41 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not whether the call itself was right; only that one was attempted.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
37.7%
Single-turn calls (curated) · rank 103 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
81.3%
Single-turn calls (curated) · rank 73 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
66.1%
Single-turn calls (user-contributed) · rank 77 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
70.8%
Single-turn calls (user-contributed) · rank 54 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
75.5%
Web search · rank 10 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not general research quality: questions have short, checkable answers.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
71.5%
Web search · rank 15 of 109
Unit
% correct, higher is better
Configuration
o4-mini
Measured
16 Dec 2025
Not shown
Not general research quality: questions have short, checkable answers.
Reported by UGI Leaderboard
19.0%
Requested-length error · rank 163 of 370
Unit
% off the requested word count, lower is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
36.0%
Requested-length error · rank 281 of 370
Unit
% off the requested word count, lower is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
27.0%
Requested-length error · rank 239 of 370
Unit
% off the requested word count, lower is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.31
Style adherence · rank 308 of 370
Unit
score from 0 to 1, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.33
Style adherence · rank 241 of 370
Unit
score from 0 to 1, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.31
Style adherence · rank 302 of 370
Unit
score from 0 to 1, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
43.2
Writing score · rank 189 of 370
Unit
score out of 100, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by UGI Leaderboard
46.9
Writing score · rank 171 of 370
Unit
score out of 100, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by UGI Leaderboard
45.4
Writing score · rank 175 of 370
Unit
score out of 100, higher is better
Configuration
o4-mini
Measured
4 Oct 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by Vectara Hallucination Leaderboard
98.7%
Answer rate · rank 74 of 108
Unit
% of documents, higher is better
Configuration
o4-mini
Measured
22 Sep 2026
Not shown
Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Reported by Vectara Hallucination Leaderboard
18.6%
Hallucination rate · rank 98 of 108
Unit
% of summaries, lower is better
Configuration
o4-mini
Measured
22 Sep 2026
Not shown
Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.

Compare o4 Mini with