ModelsCompareBest forBenchmarksStatusPricingAPI

Llama 3.3 70B Instruct

Meta·Pending·Released 2024-12-06text
Context131.072k
Max output-
Input / 1M-
Output / 1M-
Cached in-
Benchmarks5

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

GPQA Diamond (Epoch AI run)#76/7747.4% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#76/765.1% ↗
LMArena Elo#59/621274 ↗
GPQA Diamond#66/7050.5% ↗
MMLU-Pro#27/2968.9% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Meta

Llama 4 MaverickLlama 4 Scout

Access Llama 3.3 70B Instruct and every other model through one endpoint with automatic failover: Respan gateway.