Benchmark Almanac

NoticIA

ClickbaitFighter-10B 52.0 tops its leaderboard GPT-4 Turbo (Jan 2024) 32.0 leads the models we track
Not in model cards

Models summarize Spanish news articles in one sentence that answers the clickbait headline. The evaluator compares each summary with a human reference.

Released
April 2024
Kind
Faithful to sources
Level
School
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Spanish
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-3.5 Turbo Jan 2024 #200 on the capability index
Last model added
February 2024
Scores refreshed
November 20th, 2026
36
Entries in its paper, 11 models we track

ClickbaitFighter-10B tops the leaderboard with 52.0 GPT-4 Turbo (Jan 2024) leads with 32.0 among models released by February 2024

Best score per entry from the benchmark's paper, read on November 20th, 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 GPT-4 Turbo (Jan 2024), at 32.0. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 ClickbaitFighter-10B 52.0
  2. 2 ClickbaitFighter-7B 49.8
  3. 3 Meta-Llama-3-70B-Instruct 36.3
  4. 4 ClickbaitFighter-2B 36.3
  5. 5 gpt-4o (snapshot unspecified) 35.5
  6. 6 gpt-4-turbo (snapshot unspecified) 34.0
  7. 7 GPT-4 Turbo (Jan 2024) 32.0
  8. 8 Nous-Hermes-2-Yi-34B 30.0
  9. 9 DeepSeek LLM 67B 29.1
  10. 10 openchat-3.5-0106 28.4
  11. 11 Qwen1.5-72B 27.8
  12. 12 Nous-Hermes-2-SOLAR-10.7B 27.5
  13. 13 Meta-Llama-3-8B-Instruct 27.2
  14. 14 GPT-3.5 Turbo Jan 2024 27.1
  15. 15 Nous-Hermes-2-Mixtral-8x7B-SFT 27.0
  16. 16 Nous-Hermes-2-Mistral-7B-DPO 26.3
  17. 17 OpenHermes-2.5-Mistral-7B 25.9
  18. 18 Mistral-7B-Instruct-v0.2 25.3
  19. 19 Mixtral-8x7B-Instruct-v0.1 25.2
  20. 20 Qwen1.5-14B-Chat 23.9
  21. 21 Hermes-2-Pro-Mistral-7B 23.5
  22. 22 Tulu 2 DPO 70B 23.3
  23. 23 gemma-2b-it 22.2
  24. 24 gemma-7b-it 22.0
  25. 25 SOLAR-10.7B-Instruct-v1.0 21.3
  26. 26 Qwen1.5-7B-Chat 20.7
  27. 27 Nous-Hermes-2-Mixtral-8x7B-DPO 19.7
  28. 28 Llama-2-70b-chat-hf 19.2
  29. 29 Llama-2-13b-chat-hf 18.4
  30. 30 Zephyr 7B Beta 15.6
  31. 31 Llama-2-7b-chat-hf 14.7
  32. 32 stablelm-zephyr-3b 12.0
  33. 33 Nous-Hermes-2-Llama-2-70B 7.22
  34. 34 TinyLlama-1.1B-Chat-v1.0 3.84
  35. 35 Smaug-72B-v0.1 1.79
  36. 36 rocket-3B 0.92

Source: The NoticIA paper

#EntryScoreSettingDateSource
1 ClickbaitFighter-10B 52.0 Official leaderboard
2 ClickbaitFighter-7B 49.8 Official leaderboard
3 Meta-Llama-3-70B-Instruct 36.3 Official leaderboard
4 ClickbaitFighter-2B 36.3 Official leaderboard
5 gpt-4o (snapshot unspecified) 35.5 Official leaderboard
6 gpt-4-turbo (snapshot unspecified) 34.0 Official leaderboard
7 GPT-4 Turbo (Jan 2024) 32.0 Jan 2024 Official leaderboard
8 Nous-Hermes-2-Yi-34B 30.0 Official leaderboard
9 DeepSeek LLM 67B 29.1 Nov 2023 Official leaderboard
10 openchat-3.5-0106 28.4 Official leaderboard
11 Qwen1.5-72B 27.8 Feb 2024 Official leaderboard
12 Nous-Hermes-2-SOLAR-10.7B 27.5 Official leaderboard
13 Meta-Llama-3-8B-Instruct 27.2 Official leaderboard
14 GPT-3.5 Turbo Jan 2024 27.1 Jan 2024 Official leaderboard
15 Nous-Hermes-2-Mixtral-8x7B-SFT 27.0 Official leaderboard
16 Nous-Hermes-2-Mistral-7B-DPO 26.3 Official leaderboard
17 OpenHermes-2.5-Mistral-7B 25.9 Official leaderboard
18 Mistral-7B-Instruct-v0.2 25.3 Dec 2023 Official leaderboard
19 Mixtral-8x7B-Instruct-v0.1 25.2 Official leaderboard
20 Qwen1.5-14B-Chat 23.9 Feb 2024 Official leaderboard
21 Hermes-2-Pro-Mistral-7B 23.5 Official leaderboard
22 Tulu 2 DPO 70B 23.3 Nov 2023 Official leaderboard
23 gemma-2b-it 22.2 Official leaderboard
24 gemma-7b-it 22.0 Official leaderboard
25 SOLAR-10.7B-Instruct-v1.0 21.3 Dec 2023 Official leaderboard
26 Qwen1.5-7B-Chat 20.7 Feb 2024 Official leaderboard
27 Nous-Hermes-2-Mixtral-8x7B-DPO 19.7 Jan 2024 Official leaderboard
28 Llama-2-70b-chat-hf 19.2 Official leaderboard
29 Llama-2-13b-chat-hf 18.4 Official leaderboard
30 Zephyr 7B Beta 15.6 Oct 2023 Official leaderboard
31 Llama-2-7b-chat-hf 14.7 Official leaderboard
32 stablelm-zephyr-3b 12.0 Official leaderboard
33 Nous-Hermes-2-Llama-2-70B 7.22 Official leaderboard
34 TinyLlama-1.1B-Chat-v1.0 3.84 Official leaderboard
35 Smaug-72B-v0.1 1.79 Official leaderboard
36 rocket-3B 0.92 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Turbo (Jan 2024) 32.0 Jan 2024 Official leaderboard
2 DeepSeek LLM 67B 29.1 Nov 2023 Official leaderboard
3 Qwen1.5-72B 27.8 Feb 2024 Official leaderboard
4 GPT-3.5 Turbo Jan 2024 27.1 Jan 2024 Official leaderboard
5 Mistral-7B-Instruct-v0.2 25.3 Dec 2023 Official leaderboard
6 Qwen1.5-14B-Chat 23.9 Feb 2024 Official leaderboard
7 Tulu 2 DPO 70B 23.3 Nov 2023 Official leaderboard
8 SOLAR-10.7B-Instruct-v1.0 21.3 Dec 2023 Official leaderboard
9 Qwen1.5-7B-Chat 20.7 Feb 2024 Official leaderboard
10 Nous-Hermes-2-Mixtral-8x7B-DPO 19.7 Jan 2024 Official leaderboard
11 Zephyr 7B Beta 15.6 Oct 2023 Official leaderboard

Number one over time

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

OpenAI
Benchmark paper Not tested since Apr 2024

Source: The NoticIA paper

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
In the benchmark’s paper
15.0 20.0 25.0 30.0 35.0 2024 15.0 20.0 25.0 30.0 35.0 2024

Source: Official NoticIA 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 2 years ago, in February 2024, for Qwen1.5-14B-Chat. 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 (36 entries).
  • Pass Models scored 11 models we track, plus 25 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Qwen1.5-14B-Chat.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-3.5 Turbo (#200).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 11 rows for models we track and 25 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