Model comparison
DeepSeek-V3.2-Speciale vs Gemini 1.0 Pro
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
GoogleSummary
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 16.4.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | Gemini 1.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 39.1 | 27.1 |
| Released | 2025-12-01 | 2023-12-13 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 39.9 (#136), Gemini 1.0 Pro: 31.6 (#270)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1108 |
| HumanEval+ | — | 55.5% |
| MBPP+ | — | 61.4% |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Gemini 1.0 Pro: 16.4 (#292)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 1109 |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 116.97 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.0 Pro: 8.7 (#315)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LMArena Math | — | 1132 |
| MATH Level 5 | — | 11.2% |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.0 Pro: 15.5 (#286)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | — | 34% |
| LMArena Expert | — | 1059 |
| MMLU | — | 70% |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.0 Pro: 33.5 (#247)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | — | 1138 |
| LMArena Chinese | — | 1124 |
| LMArena French | — | 1144 |
| LMArena German | — | 1125 |
| LMArena Japanese | — | 1023 |
| LMArena Russian | — | 1186 |
| LMArena Spanish | — | 1118 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.0 Pro: 57.9 (#262)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | — | 1114 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.0 Pro: 34.3 (#244)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | — | 1132 |
Writing & Preference DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 46.1 (#217), Gemini 1.0 Pro: 36.2 (#259)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | — | 1149 |
| LMArena Creative Writing | — | 1130 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1139 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Gemini 1.0 Pro?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or Gemini 1.0 Pro better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 31.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and Gemini 1.0 Pro share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Gemini 1.0 Pro has 24.