DeepSeek-R1-0528
66.4%±4.9%
61.5%CI71.3%
aiqbench · LLM benchmarks
66.4%±4.9%
61.5%CI71.3%
55.6%±6.2%
49.4%CI61.8%
53.3%±7.5%
45.8%CI60.9%
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 107 | DeepSeek-R1-0528 | DeepSeek | May 2025 | $0.50 / $2.15 | 66.4% | 61.5%–71.3% | #89–250 | ||
| 120 | DeepSeek-R1-Distill-Qwen-32B | DeepSeek | — | — | 55.6% | 49.4%–61.8% | #255–778 | ||
| 122 | DeepSeek-R1 | DeepSeek | Jan 2025 | $0.70 / $2.50 | 53.3% | 45.8%–60.9% | #117–389 | ||
| 124 | DeepSeek-R1-Distill-Llama-70B | DeepSeek | Jan 2025 | $0.80 / $0.80 | 51.4% | 45.3%–57.4% | #286–643 | ||
| 125 | DeepSeek-R1-Distill-Qwen-14B | DeepSeek | — | — | 50.6% | 44.6%–56.5% | #347–812 | ||
| 129 | deepseek-r1-0528-qwen3-8b | — | — | — | 43.9% | 37.1%–50.7% | #465–920 | ||
| 142 | DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek | — | — | 21.4% | 16.1%–26.7% | #407–1029 |
Showing AIME (math) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.