DeepSeek V3.2 Speciale — Benchmarks

Benchmark scores for DeepSeek V3.2 Speciale aggregated from public leaderboards (2 boards), with how it ranks among open models and how it compares with its nearest neighbours. See hardware requirements for what you need to run it.

No llmrun Composite Score for DeepSeek V3.2 Speciale: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board — or on 3 boards that narrow its score to a 90% range of at most 15.6 points. Either way the results must come from at least two different benchmarks. Its individual scores below stand on their own — see how the llmrun Composite Score gets calculated.

DeepSeek V3.2 Speciale reasoning benchmarks

Multi-step logic and problem-solving — can the model think through a hard problem rather than recall an answer.

SimpleBench
SimpleBench is a set of everyday, common-sense and trick questions that humans answer easily but language models often get wrong. It probes basic reasoning and robustness rather than specialist knowledge.
52.6%
52.6%
median 40.8%open leader 61.1%
Overall best: Claude Fable 5 Max 81.9%
75th percentile · #7 of 25 open · #48 of 101 all
#7 of 25
#48 of 101
Independent
Epoch AI · Dec 2025

DeepSeek V3.2 Speciale coding benchmarks

Writing, editing, and fixing real code — measured by whether the resulting program actually runs and passes tests.

WeirdML
WeirdML asks models to write machine-learning code for small, deliberately unusual datasets, then runs the code and scores the accuracy it actually achieves. Built by Håvard Tveit Ihle, it rewards practical problem-solving over recognizing a familiar task.
46.7%
46.7%
median 39.5%open leader 82.6%
Overall best: GPT 6 Astra Promax 93.6%
74th percentile · #13 of 47 open · #78 of 162 all
#13 of 47
#78 of 162
Independent
Epoch AI · Dec 2025

Scores aggregated from public benchmark sources (Epoch AI: 2 boards) — each linked from the benchmark pages. llmrun does not run these benchmarks. Percentiles and ranks are among open models in the llmrun catalogue; the median and leader marks refer to the same field.