DeepSeek R1 0528 (May '25)
77.0%
no interval published
aiqbench · LLM benchmarks
77.0%
no interval published
61.7%
no interval published
51.3%
no interval published
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 | |||||
|---|---|---|---|---|---|---|---|---|---|
| 36 | DeepSeek R1 0528 (May '25) | deepseek | May 2025 | $0.50 / $2.15 | 77.0% | — | #88–250 | ||
| 92 | DeepSeek R1 (Jan '25) | deepseek | Jan 2025 | $0.70 / $2.50 | 61.7% | — | #117–389 | ||
| 114 | DeepSeek R1 0528 Qwen3 8B | deepseek | — | — | 51.3% | — | #465–919 | ||
| 140 | DeepSeek R1 Distill Qwen 14B | deepseek | — | — | 37.6% | — | #347–812 | ||
| 176 | DeepSeek R1 Distill Qwen 32B | deepseek | — | — | 27.0% | — | #255–778 | ||
| 178 | DeepSeek R1 Distill Llama 70B | deepseek | Jan 2025 | $0.80 / $0.80 | 26.6% | — | #286–643 | ||
| 188 | DeepSeek R1 Distill Llama 8B | deepseek | — | — | 23.3% | — | — | ||
| 247 | DeepSeek R1 Distill Qwen 1.5B | deepseek | — | — | 7.0% | — | #407–1029 |
Showing LiveCodeBench (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.