Model comparison
Deepseek Coder v2 vs Gemini 2.5 Pro
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 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 2.5 Pro in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Pro leads 63.7 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Gemini 2.5 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 45.0 |
| Released | 2024-06-17 | 2025-03-25 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 24 | 78 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Deepseek Coder v2: 38.1 (#183), Gemini 2.5 Pro: 42.4 (#101)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Coding | 1251 | 1452 |
| SWE-bench Verified | — | 57.6% |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| LMArena WebDev | — | 1227 |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| WeirdML | — | 54% |
| BigCodeBench Instruct | 48.2% | — |
| LiveBench Coding | — | 85.9% |
| BigCodeBench Complete | 59.7% | — |
| CadEval | — | 64% |
| ALE-Bench | — | 785.52 |
| AlgoTune | — | 1.51 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Gemini 2.5 Pro: 29.2 (#88)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | — | 32.6% |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| TheAgentCompany | — | 30.3% |
| τ²-bench Banking | — | 13.7% |
| DeepResearch Bench | — | 42.8% |
| BALROG | — | 43.3% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 55.4% |
| Vending-Bench 2 | — | 573.64 |
Reasoning Gemini 2.5 Pro leads
Deepseek Coder v2: 23.6 (#176), Gemini 2.5 Pro: 28.8 (#99)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1455 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 62.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 41% |
| CritPt | — | 2% |
| Chess Puzzles | — | 20% |
| EnigmaEval | — | 5.6% |
| LiveBench Reasoning | — | 89.8% |
| DTBench | — | 82.4% |
| LiveBench Data Analysis | — | 79.9% |
| LMCA | — | 34.8% |
| Epoch Capabilities Index | — | 145.32 |
| ForecastBench | — | 61.3 |
| LiveBench | — | 82.3% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Gemini 2.5 Pro: 32.5 (#213)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Math | 1241 | 1450 |
| FrontierMath (Tiers 1-3) | — | 24.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 84.7% |
| Omni-MATH | — | 41.6% |
| LiveBench Math | — | 90.2% |
| MATH Level 5 | — | 95.9% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 94.5% | — |
Knowledge Gemini 2.5 Pro leads
Deepseek Coder v2: 32.3 (#212), Gemini 2.5 Pro: 56.0 (#46)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Expert | 1181 | 1452 |
| GPQA Diamond | — | 85.3% |
| Humanity's Last Exam | — | 21.6% |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.6% |
| Vectara Hallucination Rate | — | 7% |
| GPQA (HELM) | — | 74.9% |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Gemini 2.5 Pro: 45.2 (#18)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | — | 1263 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| LMArena Document | — | 1421 |
| SpatialViz-Bench | — | 44.7% |
Multilingual Gemini 2.5 Pro leads
Deepseek Coder v2: 36.3 (#240), Gemini 2.5 Pro: 55.3 (#31)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1182 | 1451 |
| LMArena Chinese | 1201 | 1507 |
| LMArena French | 1185 | 1472 |
| LMArena German | 1164 | 1487 |
| LMArena Japanese | 1126 | 1461 |
| LMArena Korean | 1104 | 1434 |
| LMArena Russian | 1188 | 1461 |
| LMArena Spanish | 1153 | 1473 |
Instruction Following Gemini 2.5 Pro leads
Deepseek Coder v2: 61.7 (#242), Gemini 2.5 Pro: 75.0 (#75)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1180 | 1437 |
| LiveBench Instruction Following | — | 80.6% |
| IFEval | — | 84% |
Long Context Gemini 2.5 Pro leads
Deepseek Coder v2: 37.0 (#224), Gemini 2.5 Pro: 59.8 (#5)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1219 | 1449 |
| Fiction.LiveBench | — | 91.7% |
Writing & Preference Gemini 2.5 Pro leads
Deepseek Coder v2: 38.2 (#253), Gemini 2.5 Pro: 63.7 (#62)
| Benchmark | Deepseek Coder v2 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1191 | 1458 |
| LMArena Creative Writing | 1120 | 1454 |
| LMArena Multi-Turn | 1177 | 1453 |
| Short-Story Creative Writing | — | 83.8% |
| EQ-Bench Creative Writing | — | 1421 |
| WildBench | — | 85.7% |
| LiveBench Language | — | 67.8% |
Frequently asked questions
Is Deepseek Coder v2 better than Gemini 2.5 Pro?
Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Gemini 2.5 Pro better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemini 2.5 Pro share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemini 2.5 Pro has 78.