Models / dbrx-instruct-preview

Databricks

dbrx-instruct-preview

6 published results from 1 source. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
Databricks
Sources
1
Our benchmarks
0
Price
Not yet published

Reported by others

1,174
Business, management and finance · rank 334 of 402
Unit
Arena rating, higher is better
Range
1,161 to 1,187
Sample
3376 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,164
Creative writing · rank 328 of 407
Unit
Arena rating, higher is better
Range
1,152 to 1,176
Sample
4808 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,191
Expert prompts · rank 310 of 359
Unit
Arena rating, higher is better
Range
1,174 to 1,207
Sample
1678 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,188
Instruction following · rank 327 of 409
Unit
Arena rating, higher is better
Range
1,179 to 1,196
Sample
11274 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,196
Overall · rank 337 of 409
Unit
Arena rating, higher is better
Range
1,189 to 1,202
Sample
32191 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,176
Writing, literature and language · rank 332 of 408
Unit
Arena rating, higher is better
Range
1,167 to 1,186
Sample
7999 votes
Configuration
dbrx-instruct-preview
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.