Benchmark Almanac

SuperCLUE-Faith

GPT-5.2 93.2 leads since December 2025
Not in model cards

Models produce answers that remain faithful to a supplied source.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Faithful to sources
Level
School
Scored
Checked automatically
Answers
Short answer
Measures
Propensity
Behavior
Hallucination
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
December 2025
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 8 models we track

GPT-5.2 leads with 93.2 among models released by December 2025 GPT-5.2 leads with 93.2 among models released by December 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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 December 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 GPT-5.2 high / API 93.2
  2. 2 Gemini 3 Pro API 91.0
  3. 3 Doubao-Seed-1.6-251015(Thinking) Thinking / API 86.2
  4. 4 GLM-4.7 API 85.1
  5. 5 Tencent HY 2.0 Think API 81.8
  6. 6 DeepSeek-V3.2 API 79.5
  7. 7 Kimi K2 Thinking API 79.0
  8. 8 360zhinao3-pro API 77.7
  9. 9 MiniMax-M2.1 API 73.3
  10. 10 Qwen3-235B-A22B-Thinking Jul 2025, API 71.0

Source: Official SuperCLUE-Faith leaderboard

#EntryScoreSettingReleasedRun onSource
1 GPT-5.2 93.2 high / API Dec 2025 Dec 2025 Official leaderboard
2 Gemini 3 Pro 91.0 API Nov 2025 Dec 2025 Official leaderboard
3 Doubao-Seed-1.6-251015(Thinking) 86.2 Thinking / API Dec 2025 Official leaderboard
4 GLM-4.7 85.1 API Dec 2025 Dec 2025 Official leaderboard
5 Tencent HY 2.0 Think 81.8 API Dec 2025 Dec 2025 Official leaderboard
6 DeepSeek-V3.2 79.5 API Dec 2025 Dec 2025 Official leaderboard
7 Kimi K2 Thinking 79.0 API Nov 2025 Dec 2025 Official leaderboard
8 360zhinao3-pro 77.7 API Dec 2025 Official leaderboard
9 MiniMax-M2.1 73.3 API Dec 2025 Dec 2025 Official leaderboard
10 Qwen3-235B-A22B-Thinking Jul 2025 71.0 API Jul 2025 Dec 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GPT-5.2 93.2 high / API Dec 2025 Dec 2025 Official leaderboard
2 Gemini 3 Pro 91.0 API Nov 2025 Dec 2025 Official leaderboard
3 GLM-4.7 85.1 API Dec 2025 Dec 2025 Official leaderboard
4 Tencent HY 2.0 Think 81.8 API Dec 2025 Dec 2025 Official leaderboard
5 DeepSeek-V3.2 79.5 API Dec 2025 Dec 2025 Official leaderboard
6 Kimi K2 Thinking 79.0 API Nov 2025 Dec 2025 Official leaderboard
7 MiniMax-M2.1 73.3 API Dec 2025 Dec 2025 Official leaderboard
8 Qwen3-235B-A22B-Thinking Jul 2025 71.0 API Jul 2025 Dec 2025 Official leaderboard

4 models have held number one on the official leaderboard since 2023

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

Qwen Moonshot AI Google DeepMind OpenAI
Own leaderboard Not tested since Dec 2025
GPT-5.2 93.2

Source: Official SuperCLUE-Faith 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
70.0 75.0 80.0 85.0 90.0 95.0 2026 70.0 75.0 80.0 85.0 90.0 95.0 2026

Source: Official SuperCLUE-Faith 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 (10 entries).
  • Pass Models scored 8 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 11 months ago, in December 2025, for MiniMax-M2.1.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 8 rows for models we track and 2 other entries at the last read.
  • Pass Last read November 20th, 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