BlogLLM Benchmark Scores as Published, Side by Side
DocVQA: Results as Published
Every result the catalog holds for DocVQA: 7 models from 4 developers, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Multimodal UnderstandingMaintainer Minesh Mathew, Dimosthenis Karatzas, and C. V. JawaharIntroduced 2020Data version 2026103001, as of 2026-10-30
DocVQA is visual question answering on document images. The set has 50,000 questions defined on more than 12,000 document images. The primary score is Average Normalized Levenshtein Similarity (ANLS), so a small mismatch is not treated as a total miss. The paper also reports exact-match accuracy.
DocVQA (ANLS)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-4oOpenAI, released 2024-05-13 | 85.9 | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Claude 3.7 SonnetAnthropic, released 2025-02-24 | 84.3 | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| Llama 4 MaverickMeta, released 2025-04-05 | 94.4 | Meta, Meta Llama 4 model cardchecked 2026-10-15; printed on 1 more page | - |
| Llama 4 Maverick (pre-trained)Meta, released 2025-04-05 | 91.6 | Meta, Meta Llama 4 model cardchecked 2026-10-15 | - |
| Llama 4 ScoutMeta, released 2025-04-05 | 94.4 | Meta, Meta Llama 4 model cardchecked 2026-10-15 | - |
| Llama 4 Scout (pre-trained)Meta, released 2025-04-05 | 89.4 | Meta, Meta Llama 4 model cardchecked 2026-10-15 | - |
| Mistral Medium 3Mistral AI, released 2025-05-07 | 95.3 | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.