Models / granite-3.0-2b-instruct

IBM

granite-3.0-2b-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

1,136
Business, management and finance · rank 341 of 402
Unit
Arena rating, higher is better
Range
1,115 to 1,158
Sample
873 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,100
Creative writing · rank 354 of 407
Unit
Arena rating, higher is better
Range
1,078 to 1,121
Sample
916 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,177
Expert prompts · rank 310 of 359
Unit
Arena rating, higher is better
Range
1,149 to 1,206
Sample
407 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,132
Instruction following · rank 354 of 409
Unit
Arena rating, higher is better
Range
1,120 to 1,145
Sample
2698 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,157
Overall · rank 360 of 409
Unit
Arena rating, higher is better
Range
1,148 to 1,165
Sample
6837 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,106
Writing, literature and language · rank 362 of 408
Unit
Arena rating, higher is better
Range
1,091 to 1,122
Sample
1820 votes
Configuration
granite-3.0-2b-instruct
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.