Rankings / DeepSeek
Deepseek R1 Distill Qwen 14B
released 2025-01-20
BenchAtlas Index
as of 2026-09-11
base configuration
rank #403
10 families · 4 categories · medium
Benchmark evidence
16 results
coding
| LiveCodeBench v6 implementation=artificial-analysis | 37.6 % | independent | Artificial Analysis | |
| SciCode | 23.9 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 7.8 points | independent | Artificial Analysis | |
| AA Math Index | 55.7 points | independent | Artificial Analysis | |
| ECI | 135.4 points | independent | Epoch AI Benchmarking Hub |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 48.4 % | independent | Artificial Analysis | |
| GPQA Diamond | 44.7 % | independent | Epoch AI Benchmarking Hub 2025-03-10 | |
| Humanity's Last Exam implementation=artificial-analysis | 4.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 74.0 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 10.3 % | independent | Artificial Analysis | |
| IFBench | 22.1 % | independent | Artificial Analysis |
reasoning math
| AIME implementation=artificial-analysis | 66.7 % | independent | Artificial Analysis | |
| AIME year=2025 · implementation=artificial-analysis | 55.7 % | independent | Artificial Analysis | |
| MATH-500 implementation=artificial-analysis | 94.9 % | independent | Artificial Analysis | |
| MATH Level 5 | 87.1 % | independent | Epoch AI Benchmarking Hub 2025-03-11 | |
| OTIS Mock AIME 2024–2025 | 50.6 % | independent | Epoch AI Benchmarking Hub 2026-08-28 |