language benchmark
CSimpleQA Leaderboard
CSimpleQA is a Chinese benchmark for evaluating language models on factual answers to short questions.
Updated Sep 5, 2026
Models8
Model coverage8
MetricScore
EvidenceB
CSimpleQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score84.40% | Percentile100.00% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score84.30% | Percentile85.71% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score83.40% | Percentile71.43% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Score78.90% | Percentile57.14% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score78.40% | Percentile42.86% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score77.60% | Percentile28.57% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelDE | Score73.20% | Percentile14.29% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelDE | Score64.80% | Percentile0.00% | Participants8 | EvidenceC | Evaluated |
CSimpleQA Highlights
The leading models and scores on this benchmark.
CSimpleQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CSimpleQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is CSimpleQA?
What CSimpleQA measures and how its scores work.
CSimpleQA contains 3,000 questions across 6 major topics and 99 subtopics, covering humanities, science, engineering, culture, and society.
It measures the factuality of language models' answers to short Chinese questions using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CSimpleQA
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CSimpleQA.
Which model scores highest on CSimpleQA?
DeepSeek-V4-Pro-Max is currently ranked first with 84.40%.
What are the top three models on CSimpleQA?
The current leaders are DeepSeek-V4-Pro-Max (84.40%), Qwen3-235B-A22B-Instruct-2507 (84.30%), and Qwen3 VL 235B A22B Instruct (83.40%).
Which CSimpleQA model has the lowest official input price?
DeepSeek-V4-Flash-Max has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among CSimpleQA results?
The fastest matched records are DeepSeek-V3 (100.00 tok/s via DeepSeek).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.