Benchmark Almanac

Natural Questions

DeepSeek-V2 (MoE-236B, May 2024) 53.4% leads since May 2024
Dropped

Models answer real Google search questions. Model cards usually use the open-domain version, scored by exact match against short answers from Wikipedia.

The original task reads a full Wikipedia page, while model cards mostly report the closed-book variant.

Made by
Google
Released
January 2019
Kind
Trivia and open questions
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Strongest model tested
DeepSeek-V3 #154 on the capability index
Last in a launch post
June 2025, dropped before it saturated
Last model added
August 2025

In the authors’ words

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia page from the top 5 search results, and annotates a long answer (typically a paragraph) and a short answer (one or more entities) if present on the page, or marks null if no long/short answer is present. The public release consists of 307,373 training examples with single annotations; 7,830 examples with 5-way annotations for development data; and a further 7,842 examples with 5-way annotated sequestered as test data. We present experiments validating quality of the data. We also describe analysis of 25-way annotations on 302 examples, giving insights into human variability on the annotation task. We introduce robust metrics for the purposes of evaluating question answering systems; demonstrate high human upper bounds on these metrics; and establish baseline results using competitive methods drawn from related literature.

Abstract of Natural Questions: A Benchmark for Question Answering Research (ACL Q19-1026, CC BY 4.0)
20
Models scored in lab cards
8
Launch posts list it, from 3 labs
18
System cards report it, from 5 labs

DeepSeek-V2 (MoE-236B, May 2024) leads with 53.4% among models released by August 2025

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

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

20 models. Scroll sideways for the rest.

  1. 53.4 DeepSeek-V2 (MoE-236B, May 2024)
  2. 50.4 InternVL3.5-241B-A28B
  3. 47.0 DeepSeek LLM 67B
  4. 40.0 DeepSeek-V3
  5. 39.5 Llama 2-70B
  6. 37.5 PaLM 2-L
  7. 36.1 Gemma 3 27B
  8. 34.5 Gemma 2 27B
  9. 32.8 Llama 2-34B
  10. 31.4 Gemma 3 12B
  11. 31.2 Llama 2-13B
  12. 30.6 Mixtral 8x7B
  13. 29.2 Gemma 2 9B
  14. 28.8 Mistral 7B v0.1
  15. 25.7 Llama 2-7B
  16. 23.0 Gemma 7B
  17. 20.9 Gemma 3n E4B
  18. 20.0 Gemma 3 4B
  19. 12.5 Gemma 2B
  20. 9.48 Gemma 3 1B
  1. 1 DeepSeek-V2 (MoE-236B, May 2024) 53.4%
  2. 2 InternVL3.5-241B-A28B 50.4%
  3. 3 DeepSeek LLM 67B 47%
  4. 4 DeepSeek-V3 40%
  5. 5 Llama 2-70B 39.5%
  6. 6 PaLM 2-L 37.5%
  7. 7 Gemma 3 27B 36.1%
  8. 8 Gemma 2 27B 34.5%
  9. 9 Llama 2-34B 32.8%
  10. 10 Gemma 3 12B 31.4%
  11. 11 Llama 2-13B 31.2%
  12. 12 Mixtral 8x7B 30.6%
  13. 13 Gemma 2 9B 29.2%
  14. 14 Mistral 7B v0.1 28.8%
  15. 15 Llama 2-7B 25.7%
  16. 16 Gemma 7B 23%
  17. 17 Gemma 3n E4B 20.9%
  18. 18 Gemma 3 4B 20%
  19. 19 Gemma 2B 12.5%
  20. 20 Gemma 3 1B 9.48%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 DeepSeek-V2 (MoE-236B, May 2024) 53.4% May 2024 Lab model card
2 InternVL3.5-241B-A28B 50.4% Aug 2025 Lab model card
3 DeepSeek LLM 67B 47% Jan 2024 Lab model card
4 DeepSeek-V3 40% Dec 2024 Lab model card
5 Llama 2-70B 39.5% Jul 2023 Lab model card
6 PaLM 2-L 37.5% May 2023 Lab model card
7 Gemma 3 27B 36.1% Mar 2025 Lab model card
8 Gemma 2 27B 34.5% Jun 2024 Lab model card
9 Llama 2-34B 32.8% Jul 2023 Lab model card
10 Gemma 3 12B 31.4% Mar 2025 Lab model card
11 Llama 2-13B 31.2% Jul 2023 Lab model card
12 Mixtral 8x7B 30.6% Dec 2023 Lab model card
13 Gemma 2 9B 29.2% Jul 2024 Lab model card
14 Mistral 7B v0.1 28.8% Sep 2023 Lab model card
15 Llama 2-7B 25.7% Jul 2023 Lab model card
16 Gemma 7B 23% Feb 2024 Lab model card
17 Gemma 3n E4B 20.9% Jun 2025 Lab model card
18 Gemma 3 4B 20% Mar 2025 Lab model card
19 Gemma 2B 12.5% Mar 2024 Lab model card
20 Gemma 3 1B 9.48% Mar 2025 Lab model card

4 models have held number one in labs’ own numbers since 2023

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

Other labs Meta DeepSeek
Lab claims Not tested since Aug 2025
DeepSeek-V2 (MoE-236B, May 2024) 53.4%

Source: Labs’ model cards

Scores over time

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

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2023 2024 2025 Near the ceiling (85%) DeepSeek-V2 (MoE-236B, May 2024) DeepSeek LLM 67B Llama 2-70B 0% 20% 40% 60% 80% 100% 2023 2024 2025 Near the ceiling (85%) DeepSeek-V2 (MoE-236B, May 2024) DeepSeek LLM 67B

Source: Labs’ model cards

No launch post has listed it since June 2025

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind
Mistral AI
DeepSeek
DateLaunch postScoreAs the post writes it
Jun 26, 2025 Gemma 3n E4B 20.9 Natural Questions 5-shot (PT)
Mar 12, 2025 Gemma 3 27B 36.1 Natural Questions 5-shot (PT)
Dec 26, 2024 DeepSeek-V3 40 NaturalQuestions (EM)
Jun 27, 2024 Gemma 2 27B 34.5 Natural Questions (5-shot)
Feb 21, 2024 Gemma 7B 23 Natural Questions (5-shot)
Dec 11, 2023 Mixtral 8x7B 30.6 NQ [detailed table]
Sep 27, 2023 Mistral 7B v0.1 28.8 NQ
May 10, 2023 PaLM 2-L 37.5 NaturalQuestions (EM), 1-shot

18 system cards report it, from 5 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Aug 25, 2025 InternVL3.5-241B-A28B technical report 50.4 NaturalQuestions, OpenCompass (Table 14) Capabilities
Jul 17, 2025 Voxtral Small technical report Natural QA 5-shot, text-only, chart without printed numbers (Figure 6) Capabilities
Mar 25, 2025 Gemma 3 4B technical report 20 Natural Questions (NQ), PT, 5-shot (Table 9) Capabilities
Mar 25, 2025 Gemma 3 27B technical report 36.1 Natural Questions (NQ), PT, 5-shot (Table 9) Capabilities
Mar 25, 2025 Gemma 3 1B technical report 9.48 Natural Questions (NQ), PT, 5-shot (Table 9) Capabilities
Mar 25, 2025 Gemma 3 12B technical report 31.4 Natural Questions (NQ), PT, 5-shot (Table 9) Capabilities
Jul 31, 2024 Gemma 2 9B technical report 29.2 NQ, PT, 5-shot (Table 13) Capabilities
Jul 31, 2024 Gemma 2 27B technical report 34.5 NQ, PT, 5-shot (Table 13) Capabilities
May 7, 2024 DeepSeek-V2 (MoE-236B, May 2024) technical report 53.4 NaturalQuestions 5-shot, DeepSeek-V2 Chat (RL) (Table 3) Capabilities
Mar 13, 2024 Gemma 7B technical report 23 NQ, PT, 5-shot (Table 6) Capabilities
Mar 13, 2024 Gemma 2B technical report 12.5 NQ, PT, 5-shot (Table 6) Capabilities
Jan 8, 2024 Mixtral 8x7B technical report 30.6 NQ, 5-shot (Table 2) Capabilities
Jan 5, 2024 DeepSeek LLM 67B technical report 47 NaturalQuestions, DeepSeek 67B Chat (Table 6) Capabilities
Oct 10, 2023 Mistral 7B v0.1 technical report 28.8 NQ, 5-shot (Table 2) Capabilities
Jul 19, 2023 Llama 2-7B technical report 25.7 NaturalQuestions, exact match, 5-shot, pretrained (Table 22). 1-shot = 22.7 Capabilities
Jul 19, 2023 Llama 2-70B technical report 39.5 NaturalQuestions, exact match, 5-shot, pretrained (Table 22). 1-shot = 33.0 Capabilities
Jul 19, 2023 Llama 2-34B technical report 32.8 NaturalQuestions, exact match, 5-shot, pretrained (Table 22). 1-shot = 30.0 Capabilities
Jul 19, 2023 Llama 2-13B technical report 31.2 NaturalQuestions, exact match, 5-shot, pretrained (Table 22). 1-shot = 28.0 Capabilities

More in Knowledge

All 121 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • KMMLU-Pro In use Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry. Solar Pro 4 79.2%
  • HLE-Verified In use Verified and revised version of Humanity's Last Exam (1,811 items) with uncertain items removed. Seed2.0 Pro 73.6%