Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemini 2.0 Pro
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 37.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeek
GoogleSummary
- They share 1 benchmark with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 2 categories and Gemini 2.0 Pro in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V2.5 (Sep 2024) leads 39.5 to 29.2.
- The biggest single-benchmark swing is Aider Polyglot: 17.8% for DeepSeek-V2.5 (Sep 2024) and 35.6% for Gemini 2.0 Pro.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 39.1 |
| Released | 2024-09-06 | 2025-02-05 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemini 2.0 Pro: 37.8 (#187)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| Aider Polyglot | 17.8% | 35.6% |
| BigCodeBench Instruct | 48.6% | — |
| LiveBench Coding | — | 63.5% |
| LMArena Coding | 1309 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemini 2.0 Pro: 22.3 (#198)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| EnigmaEval | — | 0.7% |
| LiveBench Reasoning | — | 60.1% |
| LMArena Hard Prompts | 1289 | — |
| LiveBench Data Analysis | — | 68% |
| Epoch Capabilities Index | — | 135.06 |
| LiveBench | — | 65.1% |
Math Gemini 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemini 2.0 Pro: 39.7 (#100)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Math | — | 71% |
| LMArena Math | 1288 | — |
| MATH Level 5 | — | 83.5% |
Knowledge Gemini 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemini 2.0 Pro: 36.5 (#167)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Confabulations | — | 18.4% |
| LMArena Expert | 1266 | — |
Multilingual Not comparable
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemini 2.0 Pro: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Gemini 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemini 2.0 Pro: 75.5 (#59)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| LiveBench Instruction Following | — | 83.4% |
| LMArena Instruction Following | 1280 | — |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemini 2.0 Pro: 29.2 (#292)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| Fiction.LiveBench | — | 41.7% |
| LMArena Longer Query | 1301 | — |
Writing & Preference Gemini 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemini 2.0 Pro: 52.7 (#165)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.0 Pro |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |
| LiveBench Language | — | 44.9% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemini 2.0 Pro?
Gemini 2.0 Pro is the stronger model overall, scoring 39.1 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Gemini 2.0 Pro better for coding?
Gemini 2.0 Pro scores higher on coding benchmarks: 37.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 2.0 Pro share?
1 benchmark has published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 2.0 Pro has 14.