Up to four models
DeepSeek-R1 vs Gemini 2.0 Flash Thinking (Jan 2025)
On the index (GPT-4 = 100), DeepSeek-R1 scores 130 and Gemini 2.0 Flash Thinking (Jan 2025) 123. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
123107–139
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken2 of 9
DeepSeek-R1 leads Gemini 2.0 Flash Thinking (Jan 2025) by 7 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | DeepSeek-R1 | Gemini 2.0 Flash Thinking (Jan 2025) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 71.7% | 57.1% |
| Fiction.LiveBench | 69.4% | 52.8% |
| SimpleBench | 30.9% | 30.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 53.3% | 57.8% |
| Coding | ||
| Aider Polyglot | 56.9% | 18.2% |
Task length · METR
31 sec
Tests at least two of these models have taken. Bold rows are the core tests.