Llama 3 70B
Llama 3 70BCompare inonMMLU-Pro · Official board
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT OSS 20BmediumOpen+39%-99%$0.018 / $0.09
BetterGemini 3.1 Prounstated+73%+57%$2 / $12
CheaperQwQ 32BOpen+31%-93%$0.15 / $0.40CheaperLlama 3.3 70B InstructunstatedOpen+25%-95%$0.10 / $0.32CheaperGPT-4o Miniunstated+20%-91%$0.15 / $0.60ModelScoreCostPer taskWhat changes
GPT OSS 20BmediumOpen+39%-99%$0.018 / $0.09QwQ 32BOpen+31%-93%$0.15 / $0.40Llama 3.3 70B InstructunstatedOpen+25%-95%$0.10 / $0.32GPT-4o Miniunstated+20%-91%$0.15 / $0.60Llama 3.1 70B InstructunstatedOpen+19%-86%$0.40 / $0.40ModelScoreCostPer taskWhat changes
Gemini 3.1 Prounstated+73%+57%$2 / $12GPT-4ounstated+41%+53%$2.50 / $10GPT OSS 20BmediumOpen+39%-99%$0.018 / $0.09QwQ 32BOpen+31%-93%$0.15 / $0.40Llama 3.3 70B InstructunstatedOpen+25%-95%$0.10 / $0.32ModelScoreCostPer taskWhat changes
GPT OSS 20BmediumOpen+39%-99%$0.018 / $0.09QwQ 32BOpen+31%-93%$0.15 / $0.40Llama 3.3 70B InstructunstatedOpen+25%-95%$0.10 / $0.32Llama 3.1 70B InstructunstatedOpen+19%-86%$0.40 / $0.40mReflection Llama 3.1 70BOpen+14%-87%$0.35 / $0.40ModelScoreCostPer taskWhat changes
Llama 3.3 70B InstructunstatedOpen+25%—$0.10 / $0.32Llama 3.1 70B InstructunstatedOpen+19%—$0.40 / $0.40Llama 3 70B InstructOpen+6%——Llama 3.1 70Bsame—$0.72 / $0.72Llama 3.1 8B InstructunstatedOpen-16%—$0.02 / $0.04Llama 3 8B InstructOpen-22%——Llama 3.1 8B-31%—$0.22 / $0.22Llama 3 8B-33%—$0.30 / $0.60All Meta models →Benchmarks
in Chat & KnowledgeMMLU-Pro · official board52.8#13
FAQ
How much does Llama 3 70B cost?›
$2.65 per 1M input tokens and $3.50 per 1M output tokens (cheapest host: AWS Bedrock).
Is Llama 3 70B free to use?›
There is no free API; the cheapest paid price is $2.65 per 1M input tokens.
How good is Llama 3 70B, and what is it best at?›
#13 of 32 in Chat & Knowledge.
Is Llama 3 70B better than Llama 3 70B Instruct?›
On MMLU-Pro · official board, Llama 3 70B scores 52.8 vs 56.2 — lower.
How can I use Llama 3 70B?›
Through the API of AWS Bedrock.
What is Llama 3 70B?›
Llama 3 70B is a language model from Meta.
What are the best alternatives to Llama 3 70B?›
GPT OSS 20B (cheaper), Gemini 3.1 Pro (better).