Models / Step 3.5 Flash

Stepfun

Step 3.5 Flash

10 published results from 2 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
Stepfun
Sources
2
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Arena (formerly LMArena)
1,417
Overall · rank 117 of 177
Unit
Arena rating, higher is better
Range
1,414 to 1,420
Sample
59896 votes
Configuration
Step 3.5 Flash
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)
1,390
Business, management and finance · rank 142 of 402
Unit
Arena rating, higher is better
Range
1,384 to 1,397
Sample
11842 votes
Configuration
Step 3.5 Flash
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)
1,345
Creative writing · rank 159 of 407
Unit
Arena rating, higher is better
Range
1,338 to 1,352
Sample
9730 votes
Configuration
Step 3.5 Flash
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)
1,429
Expert prompts · rank 109 of 359
Unit
Arena rating, higher is better
Range
1,420 to 1,438
Sample
5312 votes
Configuration
Step 3.5 Flash
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)
1,384
Instruction following · rank 145 of 409
Unit
Arena rating, higher is better
Range
1,379 to 1,389
Sample
19307 votes
Configuration
Step 3.5 Flash
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)
1,393
Overall · rank 155 of 409
Unit
Arena rating, higher is better
Range
1,390 to 1,397
Sample
60243 votes
Configuration
Step 3.5 Flash
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
Writing, literature and language · rank 154 of 408
Unit
Arena rating, higher is better
Range
1,360 to 1,372
Sample
14757 votes
Configuration
Step 3.5 Flash
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 UGI Leaderboard
42.0%
Requested-length error · rank 295 of 370
Unit
% off the requested word count, lower is better
Configuration
Step 3.5 Flash
Measured
11 Feb 2026
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.37
Style adherence · rank 81 of 370
Unit
score from 0 to 1, higher is better
Configuration
Step 3.5 Flash
Measured
11 Feb 2026
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
45.9
Writing score · rank 173 of 370
Unit
score out of 100, higher is better
Configuration
Step 3.5 Flash
Measured
11 Feb 2026
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.

Compare Step 3.5 Flash with