Model comparison
DeepSeek-V3.1 vs Gemini 2.0 Flash (Feb 2025)
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 35.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
DeepSeek
GoogleSummary
- They share 24 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 6 categories and Gemini 2.0 Flash (Feb 2025) in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 15.2.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 63.2% for Gemini 2.0 Flash (Feb 2025).
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.8 | 35.1 |
| Released | 2025-08-21 | 2024-12-06 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Gemini 2.0 Flash (Feb 2025): 28.4 (#315)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| WeirdML | 38.4% | 25.8% |
| LMArena Coding | 1417 | 1350 |
| SWE-bench Verified (bash only) | — | 13.5% |
| Aider Polyglot | — | 38.2% |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Gemini 2.0 Flash (Feb 2025): 28.1 (#92)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | — | 11.4% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Gemini 2.0 Flash (Feb 2025): 15.2 (#318)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| SimpleBench | 40% | 31.1% |
| Kagi LLM Benchmark | 53.2% | 37.8% |
| LMArena Hard Prompts | 1417 | 1346 |
| DTBench | 82.7% | 63.2% |
| Epoch Capabilities Index | 139.92 | 135.36 |
| ARC-AGI-2 | — | 1.3% |
| EnigmaEval | — | 1.1% |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
| LiveBench | — | 66.9% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Gemini 2.0 Flash (Feb 2025): 37.9 (#146)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Math | 1420 | 1352 |
| OTIS Mock AIME 2024-2025 | — | 57.8% |
| Omni-MATH | — | 45.9% |
| LiveBench Math | — | 75.8% |
| MATH Level 5 | — | 82.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Gemini 2.0 Flash (Feb 2025): 32.0 (#213)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Expert | 1405 | 1339 |
| GPQA Diamond | — | 64.1% |
| Humanity's Last Exam | — | 6.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 55.6% |
| MMLU | — | 79.7% |
Multimodal Not comparable
DeepSeek-V3.1: —, Gemini 2.0 Flash (Feb 2025): 36.5 (#79)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Gemini 2.0 Flash (Feb 2025): 47.4 (#149)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1400 | 1342 |
| LMArena Chinese | 1469 | 1373 |
| LMArena French | 1447 | 1391 |
| LMArena German | 1411 | 1353 |
| LMArena Japanese | 1378 | 1294 |
| LMArena Korean | 1337 | 1313 |
| LMArena Russian | 1405 | 1351 |
| LMArena Spanish | 1431 | 1363 |
Instruction Following Too close to call
DeepSeek-V3.1: 73.9 (#110), Gemini 2.0 Flash (Feb 2025): 74.4 (#97)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Instruction Following | 1400 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
| IFEval | — | 84.1% |
Long Context Gemini 2.0 Flash (Feb 2025) leads
DeepSeek-V3.1: 36.3 (#232), Gemini 2.0 Flash (Feb 2025): 38.1 (#203)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Fiction.LiveBench | 52.8% | 61.1% |
| LMArena Longer Query | 1422 | 1344 |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Gemini 2.0 Flash (Feb 2025): 49.5 (#190)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1420 | 1354 |
| LMArena Creative Writing | 1401 | 1340 |
| EQ-Bench Creative Writing | 1436 | 1128 |
| LMArena Multi-Turn | 1408 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| WildBench | — | 80% |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is DeepSeek-V3.1 better than Gemini 2.0 Flash (Feb 2025)?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 35.1 on the Noometry Index.
Is DeepSeek-V3.1 or Gemini 2.0 Flash (Feb 2025) better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 28.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Gemini 2.0 Flash (Feb 2025) share?
24 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.