Models / granite-3.0-8b-instruct

IBM

granite-3.0-8b-instruct

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
IBM
Sources
1
Our benchmarks
0
Price
Not yet published

Reported by others

1,150
Business, management and finance · rank 336 of 402
Unit
Arena rating, higher is better
Range
1,127 to 1,172
Sample
813 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,137
Creative writing · rank 338 of 407
Unit
Arena rating, higher is better
Range
1,115 to 1,158
Sample
895 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,205
Expert prompts · rank 293 of 359
Unit
Arena rating, higher is better
Range
1,174 to 1,236
Sample
345 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,172
Instruction following · rank 335 of 409
Unit
Arena rating, higher is better
Range
1,160 to 1,185
Sample
2597 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,183
Overall · rank 343 of 409
Unit
Arena rating, higher is better
Range
1,174 to 1,192
Sample
6638 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,144
Writing, literature and language · rank 345 of 408
Unit
Arena rating, higher is better
Range
1,129 to 1,160
Sample
1751 votes
Configuration
granite-3.0-8b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.