BlogLLM Benchmark Scores as Published, Side by Side
Chinese SimpleQA: Results as Published
Every result the catalog holds for Chinese SimpleQA: 12 models from 6 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 General Knowledge and ReasoningMaintainer Taobao and Tmall Group (Yancheng He and co-authors)Introduced 2024Data version 2026103001, as of 2026-10-30
Chinese SimpleQA tests factual recall in Chinese with short questions across six topics and 99 subtopics. An LLM grader marks each answer correct or not, and the score is the share answered correctly.
Chinese SimpleQA
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.4OpenAI, released 2026-03-05 | 76.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: xhigh |
| o1-miniOpenAI, released 2024-09-12 | 40.3% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| GPT-4oOpenAI, released 2024-05-13 | 58.7% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Claude Opus 4.6Anthropic, released 2026-02-05 | 76.4% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max |
| Claude 3.5 SonnetAnthropic, released 2024-10-22 | 55.4% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 85.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high |
| DeepSeek-V4-Flash (Preview)DeepSeek, released 2026-04-24 | 78.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max |
| 71.5% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: non-think | |
| 73.2% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high | |
| DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-24 | 75.8% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: non-think |
| 84.4% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: max | |
| 77.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: high | |
| DeepSeek-R1DeepSeek, released 2025-01-20 | 63.7% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| DeepSeek-V3DeepSeek, released 2024-12-26 | 68% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Kimi K2.6Moonshot AI, released 2026-04-20 | 75.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
| GLM-5.1Z.ai, released 2026-04-07 | 75% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | Effort: thinking |
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.