DeepSeek
深度求索🇨🇳 30 models · China · 131 Benchmarks
Leaderboard position
#17
Company rank (of 237 companies)
Best model overall
1164
Average Elo
30
Models
131
Benchmarks covered
Above: Intern Language Models #45
Below: MiniMax #51
Model highlights
Best model
#48
2609 Elo · 10 benchmarks
Lowest-ranked model
#1104
-770 Elo · 4 benchmarks
Nearest competitor company
The company with the most similar benchmark results.
appeared as nearest in 20 of 131 benchmarks
20/131
15.3%
| Company | Votes | % of benchmarks |
|---|---|---|
| 20 | 15.3% | |
| Qwen | 14 | 10.7% |
| Moonshot AI | 11 | 8.4% |
| Anthropic | 9 | 6.9% |
| Z.ai | 8 | 6.1% |
| SpaceXAI | 7 | 5.3% |
| Xiaomi | 6 | 4.6% |
| OpenAI | 6 | 4.6% |
| Meta Llama | 5 | 3.8% |
| Yandex | 4 | 3.1% |