ChartQA — ChartQA with relaxed-accuracy metric (standard alt scoring); distinct metric axis from base chartqa
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | MiniMax VL 01 | MiniMax | 91.7 | 1 | 2026-06-12 |
| 2 | InternVL2.5-78B | OpenGVLab | 91.5 | 1 | 2026-06-12 |
| 3 | Claude 3.5 Sonnet | Anthropic | 90.8 | 1 | 2026-06-12 |
| 4 | Gemini 1.5 Pro | 88.7 | 1 | 2026-06-12 | |
| 5 | Gemini 2.0 Flash Exp | 88.3 | 1 | 2026-06-12 | |
| 6 | GPT-4o | OpenAI | 88.1 | 1 | 2026-06-12 |
| 7 | Llama 3.2 Instruct 90B (Vision) | Meta | 85.5 | 1 | 2026-06-12 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.