Across 1 shared benchmarks, Gemini Ultra scores higher on 0 and Qwen2 VL 72B Instruct on 1. The widest gap is Avg., where Qwen2 VL 72B Instruct scores 30.9 against 23.2.
| Benchmark | Gemini Ultra | Qwen2 VL 72B Instruct |
|---|---|---|
| Avg. | 23.2 | 30.9 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.