Model comparison
DeepSeek-V3.2-Speciale vs Gemini 1.5 Flash (May 2024)
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 32.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeek
GoogleSummary
- They share 1 benchmark with published results for both. DeepSeek-V3.2-Speciale scores higher in 2 categories and Gemini 1.5 Flash (May 2024) in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 20.8.
- The biggest single-benchmark swing is WeirdML: 46.7% for DeepSeek-V3.2-Speciale and 24.9% for Gemini 1.5 Flash (May 2024).
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 39.1 | 32.9 |
| Released | 2025-12-01 | 2024-05-14 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 42 |
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 1.5 Flash (May 2024): 33.9 (#233)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| WeirdML | 46.7% | 24.9% |
| BigCodeBench Instruct | — | 43.5% |
| LMArena Coding | — | 1262 |
| BigCodeBench Complete | — | 55.1% |
| HumanEval+ | — | 75.6% |
| MBPP+ | — | 67.5% |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 26.3 (#97)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| BALROG | — | 14.6% |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Gemini 1.5 Flash (May 2024): 20.8 (#212)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 1257 |
| DTBench | — | 53.8% |
| Epoch Capabilities Index | — | 129.37 |
| ForecastBench | — | 53.9 |
| PIQA | — | 87.5% |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 20.8 (#274)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.3% |
| Omni-MATH | — | 30.4% |
| LMArena Math | — | 1269 |
| MATH Level 5 | — | 61.9% |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | — | 82.4% |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 26.2 (#253)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| GPQA Diamond | — | 47.3% |
| MMLU-Pro | — | 67.8% |
| GPQA (HELM) | — | 43.7% |
| LMArena Expert | — | 1233 |
| BoolQ | — | 85.8% |
| MMLU | — | 77.9% |
Multimodal Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 35.3 (#76)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Vision | — | 1141 |
| Video-MME | — | 70.3% |
| GeoBench | — | 76% |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 43.1 (#184)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Non-English | — | 1278 |
| LMArena Chinese | — | 1295 |
| LMArena French | — | 1257 |
| LMArena German | — | 1262 |
| LMArena Japanese | — | 1252 |
| LMArena Korean | — | 1220 |
| LMArena Russian | — | 1288 |
| LMArena Spanish | — | 1242 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 67.0 (#199)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| IFEval | — | 83.1% |
| LMArena Instruction Following | — | 1258 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Gemini 1.5 Flash (May 2024): 39.0 (#182)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Longer Query | — | 1284 |
Writing & Preference Gemini 1.5 Flash (May 2024) leads
DeepSeek-V3.2-Speciale: 46.1 (#217), Gemini 1.5 Flash (May 2024): 48.9 (#190)
| Benchmark | DeepSeek-V3.2-Speciale | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1285 |
| EQ-Bench Creative Writing | 1276 | — |
| WildBench | — | 79.2% |
| LMArena Multi-Turn | — | 1253 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Gemini 1.5 Flash (May 2024)?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 32.9 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or Gemini 1.5 Flash (May 2024) better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 33.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and Gemini 1.5 Flash (May 2024) share?
1 benchmark has published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Gemini 1.5 Flash (May 2024) has 42.