Models / llama-4-maverick-17b-128e-instruct-fp8
Metallama-4-maverick-17b-128e-instruct-fp8
10 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
- Meta
- Sources
- 2
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
56.0%
Irrelevance detection · rank 94 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general refusal or safety behaviour.
18.9%
Memory · rank 47 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not long-term personal memory in a product: sessions are BFCL's scripted ones.
20.2%
Multi-turn tasks · rank 52 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
37.3%
Overall accuracy · rank 50 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (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.
100.0%
Relevance detection · rank 1 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not whether the call itself was right; only that one was attempted.
88.7%
Single-turn calls (curated) · rank 13 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (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.
73.7%
Single-turn calls (user-contributed) · rank 49 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (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.
28.0%
Web search · rank 35 of 109
- Unit
- % correct, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8 (bfcl fc)
- Measured
- 16 Dec 2025
- Not shown
- Not general research quality: questions have short, checkable answers.
100.0%
Answer rate · rank 1 of 108
- Unit
- % of documents, higher is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8
- Measured
- 22 Sep 2026
- Not shown
- Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
8.2%
Hallucination rate · rank 40 of 108
- Unit
- % of summaries, lower is better
- Configuration
- llama-4-maverick-17b-128e-instruct-fp8
- Measured
- 22 Sep 2026
- Not shown
- Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.
Compare llama-4-maverick-17b-128e-instruct-fp8 with
