Models / Llama 3.2 3B Instruct
MetaLlama 3.2 3B Instruct
17 published results from 3 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.
- Provider
- Meta
- Sources
- 3
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
1,146
Business, management and finance · rank 340 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,126 to 1,166
- Sample
- 1012 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,145
Creative writing · rank 335 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,125 to 1,164
- Sample
- 1070 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,179
Expert prompts · rank 314 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,154 to 1,204
- Sample
- 499 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,146
Instruction following · rank 347 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,135 to 1,157
- Sample
- 3171 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,167
Overall · rank 350 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,159 to 1,174
- Sample
- 7936 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,143
Writing, literature and language · rank 346 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,128 to 1,157
- Sample
- 2118 votes
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
52.1%
Irrelevance detection · rank 98 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
6.2%
Memory · rank 85 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
4.0%
Multi-turn tasks · rank 83 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
21.9%
Overall accuracy · rank 98 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- 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.
87.5%
Relevance detection · rank 27 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
82.7%
Single-turn calls (curated) · rank 63 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- 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.
58.3%
Single-turn calls (user-contributed) · rank 91 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- 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.
1.0%
Web search · rank 81 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.2-3b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
31.0%
Requested-length error · rank 258 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 19 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.36
Style adherence · rank 146 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 19 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
10.4
Writing score · rank 364 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Llama 3.2 3B Instruct
- Measured
- 19 Sep 2025
- 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 Llama 3.2 3B Instruct with
