OmniEarth-Bench
Holistic multimodal Earth-science benchmark across atmosphere, oceans, cryosphere, biosphere, land, and human-earth interaction tasks.
9rows
vqa_averageprimary metric
2026-05-27sampled
Metadata
Metrics
VQA Average, Cross-sphere, Atmosphere, Lithosphere, Oceansphere, Cryosphere, Biosphere, Human-activities
| Rank | Subject | VQA Average | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | InternVL3-72B | 33.26 | — | Imported | 2026-05-27 |
| 2 | InternVL3-7B | 33.13 | — | Imported | 2026-05-27 |
| 3 | LLaVA-Onevision-7B | 31.51 | — | Imported | 2026-05-27 |
| 4 | Claude-3.7-Sonnet | 29.07 |  Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-27 |
| 5 | Gemini-2.0 | 28.1 | — | Imported | 2026-05-27 |
| 6 | InternLM-XComposer-2.5-7B | 26.09 | — | Imported | 2026-05-27 |
| 7 | Qwen 2.5-VL-7B | 12.39 | — | Imported | 2026-05-27 |
| 8 | GPT-4o | 11.15 |  GPT-4o openai-gpt-4o | Imported | 2026-05-27 |
| 9 | Qwen 2.5-VL-72B | 10.98 |  Qwen2.5 VL 72B Instruct qwen-qwen2.5-vl-72b-instruct | Imported | 2026-05-27 |
No matching rows.