Model comparison
Deepseek Coder v2 vs Gemini 1.0 Pro
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 27.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeek
GoogleSummary
- They share 18 benchmarks with published results for both. Deepseek Coder v2 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 Coder v2 leads 34.9 to 9.3.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini 1.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 27.3 |
| Released | 2024-06-17 | 2023-12-13 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Gemini 1.0 Pro: 32.2 (#275)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1251 | 1108 |
| HumanEval+ | 82.3% | 55.5% |
| MBPP+ | 75.1% | 61.4% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Gemini 1.0 Pro: 17.1 (#296)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1109 |
| DTBench | — | 45.9% |
| Epoch Capabilities Index | — | 117.04 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Gemini 1.0 Pro: 9.3 (#321)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Math | 1241 | 1132 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 11.2% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Gemini 1.0 Pro: 15.6 (#291)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Expert | 1181 | 1059 |
| GPQA Diamond | — | 34% |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 70% |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), Gemini 1.0 Pro: 33.4 (#252)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1182 | 1138 |
| LMArena Chinese | 1201 | 1124 |
| LMArena French | 1185 | 1145 |
| LMArena German | 1164 | 1125 |
| LMArena Japanese | 1126 | 1023 |
| LMArena Russian | 1188 | 1186 |
| LMArena Spanish | 1153 | 1119 |
| LMArena Korean | 1104 | — |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.7 (#242), Gemini 1.0 Pro: 57.6 (#267)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1180 | 1114 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#224), Gemini 1.0 Pro: 34.3 (#249)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1219 | 1132 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Gemini 1.0 Pro: 36.0 (#264)
| Benchmark | Deepseek Coder v2 | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1191 | 1149 |
| LMArena Creative Writing | 1120 | 1131 |
| LMArena Multi-Turn | 1177 | 1139 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini 1.0 Pro?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 27.3 on the Noometry Index.
Is Deepseek Coder v2 or Gemini 1.0 Pro better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 32.2 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini 1.0 Pro share?
18 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 1.0 Pro has 24.