Key Specifications

SpecificationLlama 3.3 70BLlama 3.1 70B
Vendormetameta
Version3.3-70b3.1-70b
Release Date2024-12-062024-07-23
Context Window128000 tokens128000 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseLlama 3.3 Community LicenseLlama 3 Community License
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkLlama 3.3 70BLlama 3.1 70BWinner
ARC93.992.3Llama 3.3 70B
BBH83.970.2Llama 3.3 70B
GPQA52.840Llama 3.3 70B
GSM8K86.978.8Llama 3.3 70B
HUMANEVAL8779.7Llama 3.3 70B
IFEVAL79.373.7Llama 3.3 70B
MATH73.838.5Llama 3.3 70B
MMLU83.475.6Llama 3.3 70B
MUSR62.348.1Llama 3.3 70B
WINOGRANDE86.881Llama 3.3 70B

Pricing Comparison

Tier (per Mtok)Llama 3.3 70BLlama 3.1 70B
Input$0.9$0.9
Output$0.9$0.9
Cache Read$0$0
Cache Write$0$0

Llama 3.3 70B vs Llama 3.1 70B

Model Overview

Llama 3.3 70B and Llama 3.1 70B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Key Specifications

VendorRelease DateContext WindowLicense
Meta / Meta2024-12-06 / 2024-07-23128K / 128KLlama 3.3 Community License / Llama 3 Community License

Benchmark Performance

BenchmarkLlama 3.3 70BLlama 3.1 70BWinner
ARC93.992.3A
BBH (BIG-Bench Hard)83.970.2A
GPQA52.840.0A
GSM8K (Grade School Math 8K)86.978.8A
HumanEval87.079.7A
IFEval79.373.7A
MATH73.838.5A
MMLU (Massive Multitask Language Understanding)83.475.6A
MUSR62.348.1A
WinoGrande86.881.0A

Pricing Comparison

InputOutputCache ReadCache Write
— / —— / —— / —— / —

per million tokens — A / B

Strengths & Weaknesses

Llama 3.3 70B

  • ✅ MMLU score 83.4, strong knowledge reasoning.
  • ✅ HumanEval 87.0, excellent code generation.
  • ✅ GSM8K 86.9, robust math reasoning.
  • ⚠️ Proprietary, not self-hostable.

Llama 3.1 70B

  • ✅ Reliable general-purpose model.
  • ⚠️ Proprietary, not self-hostable.

Editor’s Take

Llama 3.3 70B and Llama 3.1 70B each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

FAQ

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

References

Editor's Take

See Editor's Take section.