Model comparison
Deepseek Coder v2 vs Gemini Advanced 0514
Gemini Advanced 0514 is the stronger model overall, scoring 37.7 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Gemini Advanced 0514 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini Advanced 0514 leads 48.5 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini Advanced 0514 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 37.7 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
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 Advanced 0514: 36.6 (#205)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Coding | 1251 | 1255 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Gemini Advanced 0514 leads
Deepseek Coder v2: 23.6 (#176), Gemini Advanced 0514: 24.6 (#160)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1248 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Gemini Advanced 0514: 35.5 (#181)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Math | 1241 | 1272 |
| GSM8K | 94.5% | — |
Knowledge Too close to call
Deepseek Coder v2: 32.3 (#212), Gemini Advanced 0514: 33.3 (#205)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Expert | 1181 | 1215 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Gemini Advanced 0514 leads
Deepseek Coder v2: 36.3 (#240), Gemini Advanced 0514: 42.6 (#192)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Non-English | 1182 | 1274 |
| LMArena Chinese | 1201 | 1274 |
| LMArena French | 1185 | 1307 |
| LMArena German | 1164 | 1275 |
| LMArena Japanese | 1126 | 1242 |
| LMArena Korean | 1104 | 1232 |
| LMArena Russian | 1188 | 1283 |
| LMArena Spanish | 1153 | 1242 |
Instruction Following Gemini Advanced 0514 leads
Deepseek Coder v2: 61.7 (#242), Gemini Advanced 0514: 66.0 (#212)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1253 |
Long Context Gemini Advanced 0514 leads
Deepseek Coder v2: 37.0 (#224), Gemini Advanced 0514: 38.0 (#207)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Longer Query | 1219 | 1253 |
Writing & Preference Gemini Advanced 0514 leads
Deepseek Coder v2: 38.2 (#253), Gemini Advanced 0514: 48.5 (#200)
| Benchmark | Deepseek Coder v2 | Gemini Advanced 0514 |
|---|---|---|
| LMArena Text | 1191 | 1279 |
| LMArena Creative Writing | 1120 | 1284 |
| LMArena Multi-Turn | 1177 | 1269 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini Advanced 0514?
Gemini Advanced 0514 is the stronger model overall, scoring 37.7 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Gemini Advanced 0514 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 36.6 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini Advanced 0514 share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini Advanced 0514 has 17.