Key Specifications

SpecificationCode Llama 70BCodestral
Vendormetamistral
Versioncode-llama-70bcodestral
Release Date2024-01-292024-05-29
Context Window16000 tokens32000 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseLlama 2 Community LicenseMNPL
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkCode Llama 70BCodestralWinner
ARC89.887.4Code Llama 70B
BBH72.158.3Code Llama 70B
GPQA25.332.4Codestral
GSM8K6163.3Codestral
HUMANEVAL65.669.2Codestral
IFEVAL63.859.4Code Llama 70B
MATH3429.4Code Llama 70B
MMLU62.175.1Codestral
MUSR40.147.2Codestral
WINOGRANDE75.575.8Codestral

Pricing Comparison

Tier (per Mtok)Code Llama 70BCodestral
Input$0.9$0.3
Output$0.9$0.9
Cache Read$0$0
Cache Write$0$0

Code Llama 70B vs Codestral

Model Overview

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

Key Specifications

VendorRelease DateContext WindowLicense
Meta / Mistral2024-01-29 / 2024-05-2916K / 32KLlama 2 Community License / MNPL

Benchmark Performance

BenchmarkCode Llama 70BCodestralWinner
ARC89.887.4A
BBH (BIG-Bench Hard)72.158.3A
GPQA25.332.4B
GSM8K (Grade School Math 8K)61.063.3B
HumanEval65.669.2B
IFEval63.859.4A
MATH34.029.4A
MMLU (Massive Multitask Language Understanding)62.175.1B
MUSR40.147.2B
WinoGrande75.575.8Tie

Pricing Comparison

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

per million tokens — A / B

Strengths & Weaknesses

Code Llama 70B

  • ✅ Reliable general-purpose model.
  • ⚠️ Proprietary, not self-hostable.
  • ⚠️ Context window 16K is limited.

Codestral

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

Editor’s Take

Code Llama 70B and Codestral 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.