Key Specifications

SpecificationQwen2.5 32BMistral Small 3
Vendoralibabamistral
Version2.5-32bsmall-3
Release Date2024-09-192025-01-29
Context Window131072 tokens32768 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseQwen LicenseApache 2.0
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkQwen2.5 32BMistral Small 3Winner
ARC93.991.8Qwen2.5 32B
BBH76.871.3Qwen2.5 32B
GPQA39.430.1Qwen2.5 32B
GSM8K76.379.6Mistral Small 3
HUMANEVAL6874.4Mistral Small 3
IFEVAL73.576.9Mistral Small 3
MATH39.539.2Qwen2.5 32B
MMLU78.576.9Qwen2.5 32B
MUSR54.946Qwen2.5 32B
WINOGRANDE81.978.8Qwen2.5 32B

Pricing Comparison

Tier (per Mtok)Qwen2.5 32BMistral Small 3
Input$0.35$0.2
Output$0.45$0.6
Cache Read$0$0
Cache Write$0$0

Qwen2.5 32B против Mistral Small 3

Обзор модели

Qwen2.5 32B and Mistral Small 3 are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Ключевые характеристики

ПоставщикДата выпускаОкно контекстаЛицензия
Alibaba / Mistral2024-09-19 / 2025-01-29131K / 32KQwen License / Apache 2.0

Производительность

БенчмаркQwen2.5 32BMistral Small 3Победитель
ARC93.991.8A
BBH (BIG-Bench Hard)76.871.3A
GPQA39.430.1A
GSM8K (Grade School Math 8K)76.379.6B
HumanEval68.074.4B
IFEval73.576.9B
MATH39.539.2Tie
MMLU (Massive Multitask Language Understanding)78.576.9A
MUSR54.946.0A
WinoGrande81.978.8A

Сравнение цен

ВходВыходЧтение кэшаЗапись кэша
— / —— / —— / —— / —

за миллион токенов — A / B

Сильные стороны & Слабые стороны

Qwen2.5 32B

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。

Mistral Small 3

  • ✅ 可靠的通用模型。
  • ⚠️ 闭源专有模型,不支持自托管。

Мнение редактора

Qwen2.5 32B and Mistral Small 3 each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

ЧЗВ

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.

Ссылки

Editor's Take

See Editor's Take section.