Benchmark Almanac

TruthfulQA-Multi

Gemma-2-27b-it 61.3% tops its leaderboard Llama 3.1-70B 50.6% leads the models we track
Not in model cards

Models answer questions targeting common misconceptions in Basque, Catalan, Galician and Spanish. The translations support direct comparison with the English questions.

Released
February 2025
Kind
Short factual questions
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Propensity
Behavior
Hallucination
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Based on
TruthfulQA
Strongest model tested
Llama 3.1-70B #177 on the capability index
Last model added
July 2024
Scores refreshed
November 20th, 2026
12
Entries in its paper, 6 models we track

Gemma-2-27b-it tops the leaderboard with 61.3% Llama 3.1-70B leads with 50.6% among models released by July 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 Llama 3.1-70B, at 50.6%. This view shows only models we track, each at its best.

The newest model with a score here came out in July 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 Gemma-2-27b-it 61.3%
  2. 2 Gemma-2-9b-it 58.7%
  3. 3 Llama-3-70B-Instruct 57.1%
  4. 4 Llama-3.1-70B-Instruct 54.9%
  5. 5 Llama-3-8B-Instruct 53.3%
  6. 6 Llama-3.1-8B-Instruct 53.2%
  7. 7 Llama 3.1-70B 50.6%
  8. 8 Llama 3-70B 49.5%
  9. 9 Llama 3.1-8B 46.2%
  10. 10 Gemma 2 27B 45.9%
  11. 11 Llama 3-8B 45.6%
  12. 12 Gemma 2 9B 45.6%

Source: The TruthfulQA-Multi paper

#EntryScoreSettingDateSource
1 Gemma-2-27b-it 61.3% Official leaderboard
2 Gemma-2-9b-it 58.7% Official leaderboard
3 Llama-3-70B-Instruct 57.1% Official leaderboard
4 Llama-3.1-70B-Instruct 54.9% Official leaderboard
5 Llama-3-8B-Instruct 53.3% Official leaderboard
6 Llama-3.1-8B-Instruct 53.2% Official leaderboard
7 Llama 3.1-70B 50.6% Jul 2024 Official leaderboard
8 Llama 3-70B 49.5% Apr 2024 Official leaderboard
9 Llama 3.1-8B 46.2% Jul 2024 Official leaderboard
10 Gemma 2 27B 45.9% Jun 2024 Official leaderboard
11 Llama 3-8B 45.6% Apr 2024 Official leaderboard
12 Gemma 2 9B 45.6% Jun 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Llama 3.1-70B 50.6% Jul 2024 Official leaderboard
2 Llama 3-70B 49.5% Apr 2024 Official leaderboard
3 Llama 3.1-8B 46.2% Jul 2024 Official leaderboard
4 Gemma 2 27B 45.9% Jun 2024 Official leaderboard
5 Llama 3-8B 45.6% Apr 2024 Official leaderboard
6 Gemma 2 9B 45.6% Jun 2024 Official leaderboard

Number one over time

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

Meta
Benchmark paper Not tested since Feb 2025

Source: The TruthfulQA-Multi 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 Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3.1-70B Llama 3-70B 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3.1-70B

Source: Official TruthfulQA-Multi 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in July 2024, for Llama 3.1-70B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 6 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in July 2024, for Llama 3.1-70B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3.1-70B (#177).
  • Pass Headroom The best is 50.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 6 rows for models we track and 6 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