DeepSeek-R1-Distill-Llama-70B
| Released | 2025-01-20 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 42.7 (early, few results) |
| Provider | DeepSeek |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 42.7 | 4 | |
| Overall: Coding | 41.0 | 2 | |
| Overall: Reasoning | 42.9 | 4 | |
| Overall: Agentic work | 41.0 | 2 | |
| Reasoning | 41.0 | 2 | |
| Math | 45.2 | 2 |
Evidence
Reasoning 41.0 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 55.7% | Epoch AI | 2025-03-10 |
| Kagi Reasoning Benchmark | 52.3% | Kagi | 2026-11-11 |
Math 45.2 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 89.9% | Epoch AI | 2025-03-10 |
| OTIS Mock AIME 2024-2025 | 51.4% | Epoch AI | 2025-03-07 |
Names matched to this model
deepseek-r1-distill-llama-70b