Benchmark Almanac

Known-Unknown Questions

Fine-tuned-13B-Chat 0.79 tops its leaderboard LLaMA-7B 0.56 leads the models we track
Not in model cards

Models distinguish questions with established answers from questions with no definitive answer. The authors score this distinction using F1 and equal error rate.

The ACL edition has 3,437 crowdsourced questions without definitive answers and 3,447 questions with known answers. Table 4 reports model comparisons.

Released
May 2023
Kind
Short factual questions
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Propensity
Behavior
Hallucination
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
LLaMA-13B #234 on the capability index
Last model added
February 2023
Scores refreshed
November 21st, 2026
12
Entries in its paper, 2 models we track

Fine-tuned-13B-Chat tops the leaderboard with 0.79 LLaMA-7B leads with 0.56

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is LLaMA-7B, at 0.56. This view shows only models we track, each at its best.

  1. 1 Fine-tuned-13B-Chat 0.79
  2. 2 GPT-4 (snapshot unspecified) 0.76
  3. 3 GPT-3.5 (snapshot unspecified) 0.75
  4. 4 Fine-tuned-7B-Chat 0.74
  5. 5 Llama 7B-Chat 0.74
  6. 6 Fine-tuned-13B 0.73
  7. 7 Llama 70B-Chat 0.72
  8. 8 Fine-tuned-7B 0.69
  9. 9 LLaMA-7B 0.56
  10. 10 Llama 13B-Chat 0.55
  11. 11 Llama-70B 0.51
  12. 12 LLaMA-13B 0.51

Source: The Known-Unknown Questions paper

Source: The Known-Unknown Questions paper

#EntryScoreSettingDateSource
1 Fine-tuned-13B-Chat 0.79 Official leaderboard
2 GPT-4 (snapshot unspecified) 0.76 Official leaderboard
3 GPT-3.5 (snapshot unspecified) 0.75 Official leaderboard
4 Fine-tuned-7B-Chat 0.74 Official leaderboard
5 Llama 7B-Chat 0.74 Official leaderboard
6 Fine-tuned-13B 0.73 Official leaderboard
7 Llama 70B-Chat 0.72 Official leaderboard
8 Fine-tuned-7B 0.69 Official leaderboard
9 LLaMA-7B 0.56 Feb 2023 Official leaderboard
10 Llama 13B-Chat 0.55 Official leaderboard
11 Llama-70B 0.51 Official leaderboard
12 LLaMA-13B 0.51 Feb 2023 Official leaderboard
#ModelScoreSettingDateSource
1 LLaMA-7B 0.56 Feb 2023 Official leaderboard
2 LLaMA-13B 0.51 Feb 2023 Official leaderboard

Scores over time

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

In the benchmark’s paper
0.52 0.54 0.56 2023 0.52 0.54 0.56 2023

Source: Official Known-Unknown Questions 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in February 2023, for LLaMA-13B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 2 models we track, plus 10 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in February 2023, for LLaMA-13B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is LLaMA-13B (#234).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 10 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