Benchmark Stats
Models9
Papers9
Metrics1
SOTA History
Not enough data to show trend.
accuracy
Higher is better
| Rank | Model | Source | Score | Year | Paper |
|---|---|---|---|---|---|
| 1 | Qwen2.5-VL 72B TextVQA val. Qwen2.5-VL 72B. Table 2. arxiv:2502.13923 | Community | 85.5 | 2026 | Source |
| 2 | Qwen2-VL 72B TextVQA val. Qwen2-VL 72B. Table 1. arxiv:2409.12191 | Community | 84.9 | 2026 | Source |
| 3 | InternVL2-76B TextVQA val. InternVL2-76B. Table 3. arxiv:2404.16821 | Community | 84.4 | 2026 | Source |
| 4 | Llama 3.2 Vision 90B TextVQA val. Llama 3.2 Vision 90B. Table 3. arxiv:2407.21783 | Community | 83.4 | 2026 | Source |
| 5 | Gemini 1.5 Pro TextVQA val. Gemini 1.5 Pro. Table 5. arxiv:2403.05530 | Community | 82.2 | 2026 | Source |
| 6 | GPT-4V TextVQA val. GPT-4V. Reported in multiple papers (Qwen2-VL Table 1, InternVL2 Table 3). | Community | 78 | 2026 | Source |
| 7 | GPT-4o TextVQA val. GPT-4o. System card Table 1. arxiv:2410.21276 | Community | 77.4 | 2026 | Source |
| 8 | LLaVA-1.5 TextVQA val. 13B. Table 1. arxiv:2310.03744 | Community | 61.3 | 2026 | Source |
| 9 | BLIP-2 TextVQA val. FlanT5-XXL backbone. Table 9. arxiv:2301.12597 | Community | 42.5 | 2026 | Source |