TAAROFBENCH
Models respond to 450 social scenarios where Persian taarof etiquette may or may not apply. The evaluation measures culturally appropriate responses.
On September 1, 2025, DeepSeek V3 led the baseline comparison at 56.2% overall accuracy across 450 scenarios. Llama 3 scored 54.8%.
- Made by
- Nikta Gohari Sadr and collaborators
- Released
- September 2025
- Kind
- Chat and instructions in many languages
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
DeepSeek-V3 Mar 2025 #141 on the capability index
- Last model added
- March 2025
- Scores refreshed
- November 20th, 2026
DeepSeek-V3 leads with 56.2% DeepSeek-V3 leads with 56.2%
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. This view shows only models we track, each at its best.
- 1
DeepSeek-V3 Mar 2025 56.2%
- 2 Llama 3 54.8%
Source: The TAAROFBENCH paper
- 1
DeepSeek-V3 Mar 2025 56.2%
Source: The TAAROFBENCH paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 56.2% | Mar 2025 | Official leaderboard | |
| 2 | Llama 3 | 54.8% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 56.2% | Mar 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official TAAROFBENCH 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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 20 months ago, in March 2025, for DeepSeek-V3. 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 (2 entries).
- Note Models scored Only 1 model we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 20 months ago, in March 2025, for DeepSeek-V3.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-V3 (#141).
- Pass Headroom The best is 56.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 1 row for models we track and 1 other entry 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.