BlogLLM Benchmark Scores as Published, Side by Side
OmniDocBench: Results as Published
Every result the catalog holds for OmniDocBench: 36 models from 7 developers, read from 10 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 Linke Ouyang (lead author) and co-authors; code and dataset under the opendatalab GitHub organization (OpenDataLab)Introduced 2024Data version 2026103001, as of 2026-10-30
OmniDocBench tests whether a model can parse PDF pages into structured content across varied document types, including handwritten notes and densely typeset newspapers. The paper describes nine document sources annotated with 19 layout categories and 15 attribute labels. The README gives 1,651 PDF pages across 10 document types, 5 layout types and 5 language types, and its metrics are normalized edit distance for text, TEDS for tables and CDM for formulas, combined in the leaderboard Overall score as ((1 - text Edit distance) * 100 + table TEDS + formula CDM) / 3.
OmniDocBench 1.5
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.5OpenAI, released 2026-04-23 | 87.5% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| GPT-5.2OpenAI, released 2025-12-11 | 85.7% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| GPT-5 miniOpenAI, released 2025-08-07 | 77% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 89.3% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 86.9% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 86.6% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | Effort: max |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 87.7% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 85.8% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 74.4% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Gemma 4 31BGoogle, released 2026-04-02 | 80.1% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 88.1% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 88.5% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15; printed on 1 more page | - |
| Muse Glimmer-30BMeta, released 2026-08-09 | 75.8% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Qwen3.7-PlusAlibaba, released 2026-06-01 | 91.4% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Qwen3.6-27BAlibaba, released 2026-04-22 | 89.4% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Qwen3.6-35B-A3BAlibaba, released 2026-04-16 | 89.9% | Alibaba, Qwen3.6-35B-A3B model cardchecked 2026-10-15 | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 89.8% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 88.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 89.3% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 90.8% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3-VL-235B-A22BAlibaba, released 2025-09-23 | 84.5% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Qwen3-VL-235B-A22B-ThinkingAlibaba, released 2025-09-23 | 82% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15 | - |
| Qwen3.8-27BAlibaba | 91.1% | Alibaba, Qwen3.8-27B model cardchecked 2026-10-15 | - |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 88.8% | Moonshot AI, Kimi K2.5 model cardchecked 2026-10-15; printed on 1 more page | - |
| MiniMax M3MiniMax, released 2026-06-01 | 91.6% | MiniMax, MiniMax M3checked 2026-10-15 | - |
OmniDocBench 1.5 (overall edit distance)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.4 miniOpenAI, released 2026-03-17 | 0.1263 | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: none; Tools: none |
| GPT-5.4 nanoOpenAI, released 2026-03-17 | 0.2419 | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: none; Tools: none |
| GPT-5.4OpenAI, released 2026-03-05 | 0.109 | OpenAI, Introducing GPT-5.4checked 2026-10-15; printed on 1 more page | Effort: none; Tools: none |
| GPT-5.2OpenAI, released 2025-12-11 | 0.14 | OpenAI, Introducing GPT-5.4checked 2026-10-15 | Effort: none; Tools: none |
| GPT-5 miniOpenAI, released 2025-08-07 | 0.1791 | OpenAI, Introducing GPT-5.4 mini and nanochecked 2026-10-15 | Effort: none; Tools: none |
| Gemma 4 12BGoogle, released 2026-04-02 | 0.164 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 26B A4BGoogle, released 2026-04-02 | 0.149 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 31BGoogle, released 2026-04-02 | 0.131 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 E2BGoogle, released 2026-04-02 | 0.29 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 4 E4BGoogle, released 2026-04-02 | 0.181 | Google, Gemma 4 model cardchecked 2026-10-15 | - |
| Gemma 3 27BGoogle, released 2025-03-12 | 0.365 | Google, Gemma 4 model cardchecked 2026-10-15 | Effort: no think |
OmniDocBench (version not stated)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 85.8% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15 | Effort: max |
| GPT-5.5OpenAI, released 2026-04-23 | 89.4% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15 | Effort: xhigh |
| Claude Fable 5Anthropic, released 2026-06-09 | 89.8% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15 | Effort: max; Fallback: w/ fallback |
| Claude Opus 4.8Anthropic, released 2026-05-28 | 87.9% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15 | Effort: max |
| Kimi K3Moonshot AI, released 2026-07-16 | 91.1% | Moonshot AI, Kimi K3 model cardchecked 2026-10-15 | Effort: max |
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.