DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm

DavidAU

Parameters

25.5B

Downloads

—

Likes

—

Avg score

35.3

6 benchmarks

Weights

Open

Released

—

About

DeepSeek-R1-Distill-Qwen-25.5B-Brainstorm is a 25.5B-parameter open-weights model in the DeepSeek family from DavidAU. Benchmarked on 6 evals, averaging 35.3.

Benchmark scores · 6

avg 35.3 — higher is better

MATH Lvl 5Open LLM LB · 2026-05

55.4

MMLU-ProOpen LLM LB · 2026-05

40.3

BIG-Bench HardOpen LLM LB · 2026-05

38.5

IFEvalOpen LLM LB · 2026-05

34.2

MuSROpen LLM LB · 2026-05

25.2

GPQA DiamondOpen LLM LB · 2026-05

18.1

Details

PublisherDavidAU

FamilyDeepSeek

Parameters25.5B

License

WeightsOpen

Released—

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.