Gemini 2.0 Flash Thinking (Jan 2025) is a closed-weights model from Google DeepMind, released January 21, 2025. It has an ECI score of 135 and ranks 136th of 253 tracked models. At the time of its release, it ranked 6th of 106 tracked models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 167 | 135 | 135 | 137 | 138 | |
| Ranking | #136 | #140 | #130 | #126 | |
| Conceptual reasoning | SimpleBenchBest score 82% | ||||
| Long context | Fiction.liveBenchBest score 97% | ||||
| Mathematics | OTIS Mock AIME 2024-2025Best score 100% | ||||
| Multimodal | EnigmaEvalBest score 39% | ||||
| Science | Humanity's Last ExamBest score 55% | ||||
GPQA DiamondBest score 96% | |||||
| Software engineering | Aider PolyglotBest score 88% | ||||
| Writing & creativity | Lech Mazur WritingBest score 8.6 | 7.4 | 7.2 | 7.6 | 8.0 |
| Other | LiveBenchBest score 82% |