Compare / Nanbeige4.3 33B vs DeepSeek-R1-Distill-Qwen-32B
Nanbeige4.3 33B vs DeepSeek-R1-Distill-Qwen-32B
Updated November 2026
Verdict
Nanbeige4.3 33B scores higher on the Small LM Index: 77.8 vs 50.9. On the 2 benchmarks both labs report, Nanbeige4.3 33B wins 2 and DeepSeek-R1-Distill-Qwen-32B wins 0. Both need about 23.2 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Nanbeige4.3 33B if…
- you want the strongest model overall
- you need math and reasoning
- you work with long documents
Pick DeepSeek-R1-Distill-Qwen-32B if…
- you want the more widely used model (more quantized builds and community support)
Specifications
| Nanbeige4.3 33B | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Small LM Index | 77.8 (likely 77–80) | 50.9 (likely 46–56) |
| Lab | Nanbeige (Kanzhun) · China | DeepSeek · China |
| Released | 2026-10-24 | 2025-01-20 |
| Parameters | 33.1B (dense) | 32.8B (dense) |
| Memory at 4-bit | ~23 GB | ~23.2 GB |
| Context window | 524K tokens | 128K tokens |
| Input | text | text |
| Reasoning | Always thinks | Always thinks |
| License | Apache-2.0 | MIT |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 17.8K | 348.2K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Nanbeige4.3 33B | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| GPQA Diamond Knowledge | 89.5 | 62.1 |
| AIME Math | 95.2 | 72.6 |
| LiveCodeBench Coding | ≈ 89 | 57.2 |
| Terminal-Bench Agentic | 80.9 | — |
| AA-LCR Long context | 84.0 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Nanbeige4.3 33B or DeepSeek-R1-Distill-Qwen-32B?
Nanbeige4.3 33B scores higher on the Small LM Index: 77.8 vs 50.9. On the 2 benchmarks both labs report, Nanbeige4.3 33B wins 2 and DeepSeek-R1-Distill-Qwen-32B wins 0.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 23.2 GB of memory at 4-bit quantization.
Which has the longer context window?
Nanbeige4.3 33B has the longer context window: 524K tokens against 128K.
Can I use Nanbeige4.3 33B and DeepSeek-R1-Distill-Qwen-32B commercially?
Nanbeige4.3 33B is released under Apache-2.0 and DeepSeek-R1-Distill-Qwen-32B under MIT. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.