Model
Gemini 2.5 Flash Lite
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| MS-Exam-Gen | 84.4 | accuracy | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool UseMultimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| HLR-AVSceneQA | 38.1 | accuracy | N/A | Independent | medium | arxiv.org |
| TRAJECTORY-144 | 49.2 | accuracy | tracer | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…