Up to four models
Gemini 2.0 Flash (Dec 2024) vs DeepSeek-V3
On the index (GPT-4 = 100), Gemini 2.0 Flash (Dec 2024) scores 122 and DeepSeek-V3 119. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
122106–139
WeightsClosed
ReleasedDec 2024
Price in / out–
Context–
Core tests taken0 of 9
119103–135
WeightsOpen
ReleasedDec 2024
Price in / out$0.26 / $1.03
Context164K
Core tests taken2 of 9
Gemini 2.0 Flash (Dec 2024) and DeepSeek-V3 are too close to call (3 points apart, within the uncertainty).
Test by testthird-party results
Every result as a table
| Test | Gemini 2.0 Flash (Dec 2024) | DeepSeek-V3 |
|---|---|---|
| Reasoning & knowledge | ||
| MMLU (HELM runs) | 79.7% | 87.2% |
| SimpleBench | 31.1% | 18.9% |
| Coding | ||
| Aider Polyglot | 38.2% | 48.4% |
Task length · METR
28 sec
Tests at least two of these models have taken. Bold rows are the core tests.