Models / Llama 3.3 70B Instruct
MetaLlama 3.3 70B 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
1,304
Business, management and finance · rank 231 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,296 to 1,311
- Sample
- 6618 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,285
Creative writing · rank 223 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,278 to 1,292
- Sample
- 8016 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,298
Expert prompts · rank 231 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,286 to 1,309
- Sample
- 2904 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,293
Instruction following · rank 249 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,288 to 1,298
- Sample
- 18744 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,318
Overall · rank 244 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,314 to 1,321
- Sample
- 54368 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,292
Writing, literature and language · rank 241 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,286 to 1,297
- Sample
- 13769 votes
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
53.5%
Irrelevance detection · rank 97 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
8.2%
Memory · rank 79 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
21.5%
Multi-turn tasks · rank 50 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
31.9%
Overall accuracy · rank 62 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-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.
100.0%
Relevance detection · rank 1 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
88.0%
Single-turn calls (curated) · rank 22 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-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.
76.6%
Single-turn calls (user-contributed) · rank 33 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-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.
10.0%
Web search · rank 56 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-3.3-70b-instruct
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
10.0%
Requested-length error · rank 81 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 10 Sep 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.37
Style adherence · rank 102 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 10 Sep 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
26.2
Writing score · rank 295 of 370
- Unit
- score out of 100, higher is better
- Configuration
- Llama 3.3 70B Instruct
- Measured
- 10 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 3.3 70B Instruct with
