Model comparison
Deepseek Coder v2 vs Gemini 2.0 Flash (Feb 2025)
Deepseek Coder v2 and Gemini 2.0 Flash (Feb 2025) score almost the same on the Noometry Index (35.9 vs 35.1), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
DeepSeek
GoogleSummary
- They share 19 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and Gemini 2.0 Flash (Feb 2025) in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemini 2.0 Flash (Feb 2025) leads 74.4 to 61.7.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 35.1 |
| Released | 2024-06-17 | 2024-12-06 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 54 |
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 2.0 Flash (Feb 2025): 28.4 (#315)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 45.9% |
| LMArena Coding | 1251 | 1350 |
| BigCodeBench Complete | 59.7% | 59.9% |
| SWE-bench Verified (bash only) | — | 13.5% |
| Aider Polyglot | — | 38.2% |
| WeirdML | — | 25.8% |
| LiveBench Coding | — | 63.4% |
| CadEval | — | 30% |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Gemini 2.0 Flash (Feb 2025): 28.1 (#92)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | — | 11.4% |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Gemini 2.0 Flash (Feb 2025): 15.2 (#318)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1346 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31.1% |
| Kagi LLM Benchmark | — | 37.8% |
| EnigmaEval | — | 1.1% |
| LiveBench Reasoning | — | 78.2% |
| DTBench | — | 63.2% |
| LiveBench Data Analysis | — | 69.4% |
| Epoch Capabilities Index | — | 135.36 |
| LiveBench | — | 66.9% |
| WinoGrande | 83.7% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Deepseek Coder v2: 34.9 (#190), Gemini 2.0 Flash (Feb 2025): 37.9 (#146)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Math | 1241 | 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% |
| GSM8K | 94.5% | — |
Knowledge Too close to call
Deepseek Coder v2: 32.3 (#212), Gemini 2.0 Flash (Feb 2025): 32.0 (#213)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Expert | 1181 | 1339 |
| GPQA Diamond | — | 64.1% |
| Humanity's Last Exam | — | 6.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 55.6% |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 79.7% |
Multimodal Not comparable
Deepseek Coder v2: —, Gemini 2.0 Flash (Feb 2025): 36.5 (#79)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Deepseek Coder v2: 36.3 (#240), Gemini 2.0 Flash (Feb 2025): 47.4 (#149)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1182 | 1342 |
| LMArena Chinese | 1201 | 1373 |
| LMArena French | 1185 | 1391 |
| LMArena German | 1164 | 1353 |
| LMArena Japanese | 1126 | 1294 |
| LMArena Korean | 1104 | 1313 |
| LMArena Russian | 1188 | 1351 |
| LMArena Spanish | 1153 | 1363 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Deepseek Coder v2: 61.7 (#242), Gemini 2.0 Flash (Feb 2025): 74.4 (#97)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Instruction Following | 1180 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
| IFEval | — | 84.1% |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Deepseek Coder v2: 37.0 (#224), Gemini 2.0 Flash (Feb 2025): 38.1 (#203)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Longer Query | 1219 | 1344 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Deepseek Coder v2: 38.2 (#253), Gemini 2.0 Flash (Feb 2025): 49.5 (#190)
| Benchmark | Deepseek Coder v2 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1191 | 1354 |
| LMArena Creative Writing | 1120 | 1340 |
| LMArena Multi-Turn | 1177 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| EQ-Bench Creative Writing | — | 1128 |
| WildBench | — | 80% |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini 2.0 Flash (Feb 2025)?
Deepseek Coder v2 and Gemini 2.0 Flash (Feb 2025) score almost the same on the Noometry Index (35.9 vs 35.1), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or Gemini 2.0 Flash (Feb 2025) better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 28.4 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini 2.0 Flash (Feb 2025) share?
19 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.