Model card
DeepSeek-V3.2-Speciale.
DeepSeekopen-source
§ 02 · Benchmarks
Every benchmark DeepSeek-V3.2-Speciale has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | AIME 2025 | Reasoning · Mathematical Reasoning | accuracy | 96.0% | #4 | — | source ↗ |
| 02 | LiveCodeBench | Computer Code · Code Generation | pass-1 | 88.7% | #4 | — | source ↗ |
| 03 | PLCC | Natural Language Processing · Polish Cultural Competency | grammar | 84.0% | #13 | — | source ↗ |
| 04 | PLCC | Natural Language Processing · Polish Cultural Competency | geography | 94.0% | #14 | — | source ↗ |
| 05 | HLE | Reasoning · Multi-step Reasoning | accuracy | 30.6% | #15 | — | source ↗ |
| 06 | PLCC | Natural Language Processing · Polish Cultural Competency | history | 90.0% | #16 | — | source ↗ |
| 07 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 85.7% | #18 | — | source ↗ |
| 08 | PLCC | Natural Language Processing · Polish Cultural Competency | average | 81.0% | #29 | — | source ↗ |
| 09 | PLCC | Natural Language Processing · Polish Cultural Competency | art-and-entertainment | 71.0% | #38 | — | source ↗ |
| 10 | PLCC | Natural Language Processing · Polish Cultural Competency | vocabulary | 71.0% | #42 | — | source ↗ |
| 11 | PLCC | Natural Language Processing · Polish Cultural Competency | culture-and-tradition | 76.0% | #46 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where DeepSeek-V3.2-Speciale actually performs.
§ 04 · Papers
1 paper with results for DeepSeek-V3.2-Speciale.
- 2025-12-02· 4 results
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
§ 05 · Related models
Other DeepSeek models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
sdadas/PLCC
7
results
pwc-dump
4
results
7 of 11 rows marked verified.