Key Specifications

SpecificationYi LargeYi 34B
Vendorotherother
Versionyi-largeyi-34b
Release Date2024-05-132023-11-05
Context Window32768 tokens4096 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseProprietaryApache 2.0
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkYi LargeYi 34BWinner
ARC94.887.2Yi Large
BBH77.148.8Yi Large
GPQA35.220.6Yi Large
GSM8K81.348.3Yi Large
HUMANEVAL72.235.8Yi Large
IFEVAL73.448.2Yi Large
MATH55.920.5Yi Large
MMLU82.855.5Yi Large
MUSR59.436.8Yi Large
WINOGRANDE84.171.5Yi Large

Pricing Comparison

Tier (per Mtok)Yi LargeYi 34B
Input$3$0.4
Output$3$0.4
Cache Read$0$0
Cache Write$0$0

Yi Large vs Yi 34B

Model Overview

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

Key Specifications

VendorRelease DateContext WindowLicense
Other / Other2024-05-13 / 2023-11-0532K / 4KProprietary / Apache 2.0

Benchmark Performance

BenchmarkYi LargeYi 34BWinner
ARC94.887.2A
BBH (BIG-Bench Hard)77.148.8A
GPQA35.220.6A
GSM8K (Grade School Math 8K)81.348.3A
HumanEval72.235.8A
IFEval73.448.2A
MATH55.920.5A
MMLU (Massive Multitask Language Understanding)82.855.5A
MUSR59.436.8A
WinoGrande84.171.5A

Pricing Comparison

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

per million tokens — A / B

Strengths & Weaknesses

Yi Large

  • ✅ MMLU score 82.8, strong knowledge reasoning.
  • ⚠️ Proprietary, not self-hostable.

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.

Editor’s Take

Yi Large and Yi 34B 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.