Benchmark Almanac

SuperCLUE-Fact

DeepSeek-R1 May 2025 86.0 leads since May 2025
Not in model cards

Models answer short Chinese questions and identify false statements involving knowledge, common sense, misleading prompts and context.

SuperCLUE publishes scores for 12 models in its 2025 results workbook.

Made by
SuperCLUE
Released
April 2025
Kind
Short factual questions
Level
School
Scored
Checked automatically
Answers
Short answer
Measures
Propensity
Behavior
Hallucination
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Run by
A host
Strongest model tested
Gemini 2.5 Pro Jun 2025 #97 on the capability index
Last model added
June 2025
Scores refreshed
November 21st, 2026
12
Entries on its own leaderboard, 7 models we track

DeepSeek-R1 leads with 86.0 among models released by June 2025 DeepSeek-R1 leads with 86.0 among models released by June 2025

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 DeepSeek-R1 May 2025 86.0
  2. 2 GPT-4.5 85.3
  3. 3 Gemini 2.5 Pro Jun 2025 85.0
  4. 4 Claude 3.7 Sonnet(Extended) 84.2
  5. 5 ChatGPT-4o-latest 83.2
  6. 6 DeepSeek-V3 Mar 2025 82.8
  7. 7 doubao-1.5-pro-32k 81.7
  8. 8 qwen-max-latest 79.9
  9. 9 QwQ-32B 78.8
  10. 10 o3-mini high 78.8
  11. 11 Gemini 2.0 Flash Feb 2025 78.5
  12. 12 ernie-4.5-8k-preview 77.8

Source: Official SuperCLUE-Fact leaderboard

#EntryScoreSettingDateSource
1 DeepSeek-R1 May 2025 86.0 May 2025 Official leaderboard
2 GPT-4.5 85.3 Feb 2025 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 85.0 Jun 2025 Official leaderboard
4 Claude 3.7 Sonnet(Extended) 84.2 Official leaderboard
5 ChatGPT-4o-latest 83.2 Official leaderboard
6 DeepSeek-V3 Mar 2025 82.8 Mar 2025 Official leaderboard
7 doubao-1.5-pro-32k 81.7 Official leaderboard
8 qwen-max-latest 79.9 Official leaderboard
9 QwQ-32B 78.8 Mar 2025 Official leaderboard
10 o3-mini 78.8 high Jan 2025 Official leaderboard
11 Gemini 2.0 Flash Feb 2025 78.5 Feb 2025 Official leaderboard
12 ernie-4.5-8k-preview 77.8 Official leaderboard
#ModelScoreSettingDateSource
1 DeepSeek-R1 May 2025 86.0 May 2025 Official leaderboard
2 GPT-4.5 85.3 Feb 2025 Official leaderboard
3 Gemini 2.5 Pro Jun 2025 85.0 Jun 2025 Official leaderboard
4 DeepSeek-V3 Mar 2025 82.8 Mar 2025 Official leaderboard
5 QwQ-32B 78.8 Mar 2025 Official leaderboard
6 o3-mini 78.8 high Jan 2025 Official leaderboard
7 Gemini 2.0 Flash Feb 2025 78.5 Feb 2025 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 知识幻觉, 常识幻觉 and 对抗性幻觉. Gemini 2.5 Pro leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

知识幻觉

7 models we track have a score here.

  1. 1 DeepSeek-V3 Mar 2025 ↑3 93.1
  2. 2 Gemini 2.5 Pro Jun 2025 ↑1 90.5
  3. 3 GPT-4.5 ↓1 89.7
  4. 4 DeepSeek-R1 May 2025 ↓3 89.7
  5. 5 Gemini 2.0 Flash Feb 2025 ↑2 88.8
  6. 6 o3-mini 86.2
  7. 7 QwQ-32B ↓2 82.8

2 models have held number one on the official leaderboard since its release in April 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI DeepSeek
Own leaderboard Not tested since Jun 2025

Source: Official SuperCLUE-Fact leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
78.0 80.0 82.0 84.0 86.0 88.0 2025 78.0 80.0 82.0 84.0 86.0 88.0 2025

Source: Official SuperCLUE-Fact leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Factuality

All 164 in Factuality
  • SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references. Qwen3.7-Plus 81.7%
  • HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy. Keye-VL-2.0-30B-A3B 73.5%
  • SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge. Gemini 3.1 Pro 77.5%
  • AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones. Inkling 2 Small 16.1
  • GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages. Amazon Nova Pro 60.7%
  • Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. GPT-6 Astra 4.20%

Data audit

7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 7 models we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 7 rows for models we track and 5 other entries at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check