Model comparison
DeepSeek-V3.1 vs Gemini 1.0 Pro
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 27.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeek
GoogleSummary
- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Gemini 1.0 Pro in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 9.3.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 45.9% for Gemini 1.0 Pro.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Gemini 1.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.8 | 27.3 |
| Released | 2025-08-21 | 2023-12-13 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 24 |
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 1.0 Pro: 32.2 (#275)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1417 | 1108 |
| WeirdML | 38.4% | — |
| HumanEval+ | — | 55.5% |
| MBPP+ | — | 61.4% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1109 |
| DTBench | 82.7% | 45.9% |
| Epoch Capabilities Index | 139.92 | 117.04 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Math | 1420 | 1132 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 11.2% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Expert | 1405 | 1059 |
| GPQA Diamond | — | 34% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | — | 70% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1400 | 1138 |
| LMArena Chinese | 1469 | 1124 |
| LMArena French | 1447 | 1145 |
| LMArena German | 1411 | 1125 |
| LMArena Japanese | 1378 | 1023 |
| LMArena Russian | 1405 | 1186 |
| LMArena Spanish | 1431 | 1119 |
| LMArena Korean | 1337 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1400 | 1114 |
Long Context DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.3 (#232), Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1422 | 1132 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | DeepSeek-V3.1 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1420 | 1149 |
| LMArena Creative Writing | 1401 | 1131 |
| LMArena Multi-Turn | 1408 | 1139 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Gemini 1.0 Pro?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 27.3 on the Noometry Index.
Is DeepSeek-V3.1 or Gemini 1.0 Pro better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 32.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Gemini 1.0 Pro share?
18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemini 1.0 Pro has 24.