llama-v3p3-70B-instruct: benchmark results
Meta's Llama 3.3 70B Instruct tracked under its Fireworks API identifier (llama-v3p3-70b-instruct). Provider: Meta. Released 2024-12-06.
Aggregate Rating 1565 ± 51, rank #1484 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GSMA Open-Telco - srsRAN-Bench | 85.33 | Score (%) | 95.5 |
| GSMA Open-Telco - 3GPP | 52 | Score (%) | 62.9 |
| GSMA Open-Telco LLM Leaderboard | 54.66 | Average Score (%) | 52.8 |
| GSMA Open-Telco - TeleQnA | 77.3 | Score (%) | 51.7 |
| GSMA Open-Telco - ORAN-Bench | 76 | Score (%) | 50 |
| GSMA Open-Telco - TeleMath | 45 | Score (%) | 48.3 |
| GSMA Open-Telco - TeleTables | 29 | Score (%) | 42.7 |
| GSMA Open-Telco - TeleLogs | 18 | Score (%) | 40.4 |
| WebApp1K | 33.4 | Pass@1 (%) | 27.3 |
Interactive version: theaggregate.ai/model?slug=llama-v3p3-70b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.