Jamba 1.5 Large vs Mistral Large 2: Benchmark Comparison
Detailed comparison of Jamba 1.5 Large and Mistral Large 2 covering benchmarks, pricing, context window, and compliance.
Key Specifications
| Specification | Jamba 1.5 Large | Mistral Large 2 |
|---|---|---|
| Vendor | other | mistral |
| Version | jamba-1-5-large | large-2 |
| Release Date | 2024-08-07 | 2024-07-24 |
| Context Window | 256000 tokens | 128000 tokens |
| Input Modalities | text | text |
| Output Modalities | text | text |
| License | Jamba Open Model License | Mistral Research License |
| SOC2 | ✗ | ✓ |
| HIPAA | ✗ | ✗ |
| GDPR | ✗ | ✓ |
| ISO 27001 | ✗ | ✓ |
Benchmark Results
| Benchmark | Jamba 1.5 Large | Mistral Large 2 | Winner |
|---|---|---|---|
| ARC | 93.8 | — | Jamba 1.5 Large |
| BBH | 82.8 | 81 | Jamba 1.5 Large |
| GPQA | 50.8 | — | Jamba 1.5 Large |
| GSM8K | 83.5 | 93 | Mistral Large 2 |
| HUMANEVAL | 73.7 | 92 | Mistral Large 2 |
| IFEVAL | 70.8 | — | Jamba 1.5 Large |
| MATH | 60 | 71 | Mistral Large 2 |
| MMLU | 84.3 | 84 | Jamba 1.5 Large |
| MUSR | 51.1 | — | Jamba 1.5 Large |
| WINOGRANDE | 84.3 | — | Jamba 1.5 Large |
Pricing Comparison
| Tier (per Mtok) | Jamba 1.5 Large | Mistral Large 2 |
|---|---|---|
| Input | $2 | $2 |
| Output | $8 | $6 |
| Cache Read | $0 | $0 |
| Cache Write | $0 | $0 |
Jamba 1.5 Large kontra Mistral Large 2
Przegląd modelu
Jamba 1.5 Large and Mistral Large 2 are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.
Kluczowe specyfikacje
| Dostawca | Data wydania | Okno kontekstowe | Licencja |
|---|---|---|---|
| Other / Mistral | 2024-08-07 / 2024-07-24 | 256K / 128K | Jamba Open Model License / Mistral Research License |
Wydajność benchmarków
| Benchmark | Jamba 1.5 Large | Mistral Large 2 | Zwycięzca |
|---|---|---|---|
| ARC | 93.8 | — | A |
| BBH (BIG-Bench Hard) | 82.8 | 81.0 | A |
| GPQA | 50.8 | — | A |
| GSM8K (Grade School Math 8K) | 83.5 | 93.0 | B |
| HumanEval | 73.7 | 92.0 | B |
| IFEval | 70.8 | — | A |
| MATH | 60.0 | 71.0 | B |
| MMLU (Massive Multitask Language Understanding) | 84.3 | 84.0 | Tie |
| MUSR | 51.1 | — | A |
| WinoGrande | 84.3 | — | A |
Porównanie cen
| Wejście | Wyjście | Odczyt pamięci podręcznej | Zapis pamięci podręcznej |
|---|---|---|---|
| — / — | — / — | — / — | — / — |
za milion tokenów — A / B
Mocne strony & Słabe strony
Jamba 1.5 Large
- ✅ MMLU score 84.3, strong knowledge reasoning.
- ✅ 上下文窗口 256K，支持长文本。
- ✅ 采用 MoE 混合专家架构。
- ⚠️ 闭源专有模型，不支持自托管。
Mistral Large 2
- ✅ MMLU score 84.0, strong knowledge reasoning.
- ✅ HumanEval 92.0, excellent code generation.
- ✅ GSM8K 93.0, robust math reasoning.
- ⚠️ 闭源专有模型，不支持自托管。
Opinia redakcji
Jamba 1.5 Large and Mistral Large 2 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.
Referencje
Editor's Take
See Editor's Take section.