Gemini 2.0 Flash (01-21) (Thinking): benchmark results
January 21 Gemini 2.0 Flash thinking experimental snapshot, kept separate from the generic thinking row. Provider: Google. Released 2025-01-21. Access: API.
Aggregate Rating 1582 ± 23, rank #759 of 2168 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| U-MATH - Algebra | 89.44 | Accuracy (%) | 98.5 |
| SuperCLUE General (March 2025) - Text Understanding and Creation | 81.16 | Score | 97.1 |
| U-MATH | 83.64 | Accuracy (%) | 97 |
| U-MATH - Differential Calculus | 70.45 | Accuracy (%) | 97 |
| U-MATH - Multivariable Calculus | 83.71 | Accuracy (%) | 97 |
| U-MATH - Integral Calculus | 82.21 | Accuracy (%) | 95.5 |
| SuperCLUE-VLM (February 2025) - Overall | 63.33 | Score | 94.1 |
| U-MATH - Sequences & Series | 88.31 | Accuracy (%) | 90.9 |
| U-MATH - Precalculus | 92.5 | Accuracy (%) | 87.9 |
| SuperCLUE General (March 2025) - Math Reasoning | 83.33 | Score | 87.1 |
| SuperCLUE General (March 2025) - Precise Instruction Following | 33.6 | Score | 81.4 |
| NYT Connections Original | 37 | Score (%) | 78.6 |
Interactive version: theaggregate.ai/model?slug=gemini-2-0-flash-01-21-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.