Model comparison
DeepSeek-V3.1 vs Gemini 2.0 Pro
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 39.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeek
GoogleSummary
- They share 2 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 5 categories and Gemini 2.0 Pro in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 52.7.
- The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 41.7% for Gemini 2.0 Pro.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Gemini 2.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.8 | 39.1 |
| Released | 2025-08-21 | 2025-02-05 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 14 |
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 Pro: 37.8 (#187)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| Aider Polyglot | — | 35.6% |
| WeirdML | 38.4% | — |
| LiveBench Coding | — | 63.5% |
| LMArena Coding | 1417 | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Gemini 2.0 Pro: 22.3 (#198)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| Epoch Capabilities Index | 139.92 | 135.06 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| EnigmaEval | — | 0.7% |
| LiveBench Reasoning | — | 60.1% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LiveBench Data Analysis | — | 68% |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
| LiveBench | — | 65.1% |
Math Too close to call
DeepSeek-V3.1: 38.9 (#122), Gemini 2.0 Pro: 39.7 (#100)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Math | — | 71% |
| LMArena Math | 1420 | — |
| MATH Level 5 | — | 83.5% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Gemini 2.0 Pro: 36.5 (#167)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Confabulations | — | 18.4% |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual Not comparable
DeepSeek-V3.1: 51.6 (#106), Gemini 2.0 Pro: —
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Gemini 2.0 Pro leads
DeepSeek-V3.1: 73.9 (#110), Gemini 2.0 Pro: 75.5 (#59)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Instruction Following | — | 83.4% |
| LMArena Instruction Following | 1400 | — |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Gemini 2.0 Pro: 29.2 (#292)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| Fiction.LiveBench | 52.8% | 41.7% |
| LMArena Longer Query | 1422 | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Gemini 2.0 Pro: 52.7 (#165)
| Benchmark | DeepSeek-V3.1 | Gemini 2.0 Pro |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
| LiveBench Language | — | 44.9% |
Frequently asked questions
Is DeepSeek-V3.1 better than Gemini 2.0 Pro?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 39.1 on the Noometry Index.
Is DeepSeek-V3.1 or Gemini 2.0 Pro better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 37.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Gemini 2.0 Pro share?
2 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 2.0 Pro has 14.