Model comparison
Deepseek Coder v2 vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 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 0 categories and Gemini 3.1 Pro Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 23.6.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 56.7 |
| Released | 2024-06-17 | 2026-02-19 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 24 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 38.1 (#183), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Coding | 1251 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| BigCodeBench Instruct | 48.2% | — |
| MirrorCode | — | 8.9% |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 23.6 (#176), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1485 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.1% |
| LMCA | — | 53.8% |
| Epoch Capabilities Index | — | 154.77 |
| ForecastBench | — | 59 |
| WinoGrande | 83.7% | — |
Math Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 34.9 (#190), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Math | 1241 | 1485 |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
| GSM8K | 94.5% | — |
Knowledge Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 32.3 (#212), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Expert | 1181 | 1485 |
| GPQA Diamond | — | 94.4% |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 36.3 (#240), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1182 | 1477 |
| LMArena Chinese | 1201 | 1529 |
| LMArena French | 1185 | 1487 |
| LMArena German | 1164 | 1491 |
| LMArena Japanese | 1126 | 1493 |
| LMArena Korean | 1104 | 1455 |
| LMArena Russian | 1188 | 1498 |
| LMArena Spanish | 1153 | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 61.7 (#242), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1180 | 1466 |
Long Context Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 37.0 (#224), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1219 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
Deepseek Coder v2: 38.2 (#253), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Deepseek Coder v2 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1191 | 1481 |
| LMArena Creative Writing | 1120 | 1482 |
| LMArena Multi-Turn | 1177 | 1488 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini 3.1 Pro Preview share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 3.1 Pro Preview has 71.