Yi 34B vs Yi 6B: Benchmark Comparison
Detailed comparison of Yi 34B and Yi 6B covering benchmarks, pricing, context window, and compliance.
Key Specifications
| Specification | Yi 34B | Yi 6B |
|---|---|---|
| Vendor | other | other |
| Version | yi-34b | yi-6b |
| Release Date | 2023-11-05 | 2023-11-05 |
| Context Window | 4096 tokens | 4096 tokens |
| Input Modalities | text | text |
| Output Modalities | text | text |
| License | Apache 2.0 | Apache 2.0 |
| SOC2 | ✗ | ✗ |
| HIPAA | ✗ | ✗ |
| GDPR | ✗ | ✗ |
| ISO 27001 | ✗ | ✗ |
Benchmark Results
| Benchmark | Yi 34B | Yi 6B | Winner |
|---|---|---|---|
| ARC | 87.2 | 88.4 | Yi 6B |
| BBH | 48.8 | 55.3 | Yi 6B |
| GPQA | 20.6 | 26.3 | Yi 6B |
| GSM8K | 48.3 | 37 | Yi 34B |
| HUMANEVAL | 35.8 | 42.3 | Yi 6B |
| IFEVAL | 48.2 | 54.9 | Yi 6B |
| MATH | 20.5 | 29.9 | Yi 6B |
| MMLU | 55.5 | 68 | Yi 6B |
| MUSR | 36.8 | 29.5 | Yi 34B |
| WINOGRANDE | 71.5 | 72.2 | Yi 6B |
Pricing Comparison
| Tier (per Mtok) | Yi 34B | Yi 6B |
|---|---|---|
| Input | $0.4 | $0.18 |
| Output | $0.4 | $0.18 |
| Cache Read | $0 | $0 |
| Cache Write | $0 | $0 |
Yi 34B 対 Yi 6B
モデル概要
Yi 34B and Yi 6B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.
主要仕様
| ベンダー | リリース日 | コンテキストウィンドウ | ライセンス |
|---|---|---|---|
| Other / Other | 2023-11-05 / 2023-11-05 | 4K / 4K | Apache 2.0 / Apache 2.0 |
ベンチマークパフォーマンス
| ベンチマーク | Yi 34B | Yi 6B | 勝者 |
|---|---|---|---|
| ARC | 87.2 | 88.4 | B |
| BBH (BIG-Bench Hard) | 48.8 | 55.3 | B |
| GPQA | 20.6 | 26.3 | B |
| GSM8K (Grade School Math 8K) | 48.3 | 37.0 | A |
| HumanEval | 35.8 | 42.3 | B |
| IFEval | 48.2 | 54.9 | B |
| MATH | 20.5 | 29.9 | B |
| MMLU (Massive Multitask Language Understanding) | 55.5 | 68.0 | B |
| MUSR | 36.8 | 29.5 | A |
| WinoGrande | 71.5 | 72.2 | B |
料金比較
| 入力 | 出力 | キャッシュ読み取り | キャッシュ書き込み |
|---|---|---|---|
| — / — | — / — | — / — | — / — |
100万トークンあたり — A / B
強み & 弱み
Yi 34B
- ✅ 可靠的通用模型。
- ⚠️ MMLU 仅 55.5，知识推理偏弱。
- ⚠️ HumanEval 35.8，代码能力较弱。
- ⚠️ 闭源专有模型，不支持自托管。
- ⚠️ 上下文窗口 4K 偏小。
Yi 6B
- ✅ 可靠的通用模型。
- ⚠️ HumanEval 42.3，代码能力较弱。
- ⚠️ 闭源专有模型，不支持自托管。
- ⚠️ 上下文窗口 4K 偏小。
編集者コメント
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.
参考文献
Editor's Take
See Editor's Take section.