DeepSeek-R1-Distill-Qwen-32B
R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving
- Strongest at
- Math Better than 30% of the past year's models · one benchmark so far
- Context window
- 131.1K tokens in · 32.8K out
Capability profile
Where it lands among 91 models released in the past year. 50 is the average model.
This modelEvery model from the past year
Coding
No results yet
Writing
No results yet
Reading & documents
No results yet
Reasoning
No results yet
Math
50Better than 30% · 1 test
Science
50Better than 8% · 1 test
Visual reasoning
No results yet
Computer use
No results yet
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow marker rests on a single benchmark.
- Math OTIS Mock AIME 2024-2025
- Science GPQA diamond
Epoch benchmark boards
Best result on each board it has run. The tick marks the leader.
Balrog20%#26 of 39
DeepSeek's past year
9 release days in the past year, about one every 41 days. The next is expected around Nov 28, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOctNov
Specifications
RELEASE DATEJan 20, 2025
WEIGHTSOpen weights
CONTEXT WINDOW131.1K
MAX OUTPUT32.8K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext
OUTPUTStext
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.