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 134 and ranks 148th of 240 tracked models. At the time of its release, it ranked 5th of 89 tracked models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 173 | 134 | 130 | 141 | 139 | |
| Ranking | #148 | #156 | #117 | #129 | |
| Conceptual reasoning | SimpleBenchBest score 95% | ||||
| 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 97% | |||||
| Software engineering | Aider PolyglotBest score 88% | ||||
| Writing & creativity | Lech Mazur WritingBest score 8.6 | 7.4 | — | 7.0 | 8.3 |
| Other | LiveBenchBest score 82% |