Model comparison
Deepseek Coder v2 vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 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 3.8 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 23.6.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini 3.8 Flash | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 61.8 |
| Released | 2024-06-17 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 24 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Deepseek Coder v2: 38.1 (#183), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Coding | 1251 | 1510 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1584 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| WeirdML | — | 84.8% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 1,270 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
Deepseek Coder v2: 23.6 (#176), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1508 |
| ARC-AGI-2 | — | 89.2% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 156.71 |
| WinoGrande | 83.7% | — |
Math Gemini 3.8 Flash leads
Deepseek Coder v2: 34.9 (#190), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Math | 1241 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
| GSM8K | 94.5% | — |
Knowledge Gemini 3.8 Flash leads
Deepseek Coder v2: 32.3 (#212), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Expert | 1181 | 1524 |
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1314 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
Deepseek Coder v2: 36.3 (#240), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1182 | 1491 |
| LMArena Chinese | 1201 | 1554 |
| LMArena French | 1185 | 1498 |
| LMArena German | 1164 | 1493 |
| LMArena Japanese | 1126 | 1502 |
| LMArena Korean | 1104 | 1459 |
| LMArena Russian | 1188 | 1515 |
| LMArena Spanish | 1153 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Deepseek Coder v2: 61.7 (#242), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1180 | 1490 |
Long Context Gemini 3.8 Flash leads
Deepseek Coder v2: 37.0 (#224), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1219 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
Deepseek Coder v2: 38.2 (#253), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Deepseek Coder v2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1191 | 1499 |
| LMArena Creative Writing | 1120 | 1492 |
| LMArena Multi-Turn | 1177 | 1501 |
| EQ-Bench Creative Writing | — | 1748 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini 3.8 Flash share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 3.8 Flash has 50.