Models / granite-3.1-8b-instruct
IBMgranite-3.1-8b-instruct
14 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
- IBM
- Sources
- 2
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,225
Business, management and finance · rank 290 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,193 to 1,258
- Sample
- 316 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,171
Creative writing · rank 311 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,144 to 1,197
- Sample
- 450 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,236
Expert prompts · rank 265 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,200 to 1,271
- Sample
- 237 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,193
Instruction following · rank 319 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,176 to 1,210
- Sample
- 1258 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,208
Overall · rank 330 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,197 to 1,220
- Sample
- 3090 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,180
Writing, literature and language · rank 326 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,159 to 1,200
- Sample
- 837 votes
- Configuration
- granite-3.1-8b-instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
80.0%
Irrelevance detection · rank 58 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
14.4%
Memory · rank 59 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
7.5%
Multi-turn tasks · rank 76 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
27.1%
Overall accuracy · rank 80 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- 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.
68.8%
Relevance detection · rank 80 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
78.3%
Single-turn calls (curated) · rank 78 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- 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.
60.3%
Single-turn calls (user-contributed) · rank 86 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- 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.
0.5%
Web search · rank 86 of 109
- Unit
- % correct, higher is better
- Configuration
- granite-3.1-8b-instruct (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
Compare granite-3.1-8b-instruct with
