Key Specifications

SpecificationYi 34BYi 6B
Vendorotherother
Versionyi-34byi-6b
Release Date2023-11-052023-11-05
Context Window4096 tokens4096 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseApache 2.0Apache 2.0
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkYi 34BYi 6BWinner
ARC87.288.4Yi 6B
BBH48.855.3Yi 6B
GPQA20.626.3Yi 6B
GSM8K48.337Yi 34B
HUMANEVAL35.842.3Yi 6B
IFEVAL48.254.9Yi 6B
MATH20.529.9Yi 6B
MMLU55.568Yi 6B
MUSR36.829.5Yi 34B
WINOGRANDE71.572.2Yi 6B

Pricing Comparison

Tier (per Mtok)Yi 34BYi 6B
Input$0.4$0.18
Output$0.4$0.18
Cache Read$0$0
Cache Write$0$0

Yi 34B vs Yi 6B

Model Overview

Yi 34B and Yi 6B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Key Specifications

VendorRelease DateContext WindowLicense
Other / Other2023-11-05 / 2023-11-054K / 4KApache 2.0 / Apache 2.0

Benchmark Performance

BenchmarkYi 34BYi 6BWinner
ARC87.288.4B
BBH (BIG-Bench Hard)48.855.3B
GPQA20.626.3B
GSM8K (Grade School Math 8K)48.337.0A
HumanEval35.842.3B
IFEval48.254.9B
MATH20.529.9B
MMLU (Massive Multitask Language Understanding)55.568.0B
MUSR36.829.5A
WinoGrande71.572.2B

Pricing Comparison

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

per million tokens — A / B

Strengths & Weaknesses

Yi 34B

  • ✅ Reliable general-purpose model.
  • ⚠️ MMLU 55.5, weak knowledge reasoning.
  • ⚠️ HumanEval 35.8, coding weak.
  • ⚠️ Proprietary, not self-hostable.
  • ⚠️ Context window 4K is limited.

Yi 6B

  • ✅ Reliable general-purpose model.
  • ⚠️ HumanEval 42.3, coding weak.
  • ⚠️ Proprietary, not self-hostable.
  • ⚠️ Context window 4K is limited.

Editor’s Take

Yi 34B and Yi 6B 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.