Human or AI? (Skills IL)
Models write short Hebrew texts on the same assignments as human authors. Readers guess who wrote each text.
The board reports human judgments for 14 models. Each score requires at least 150 counted guesses and measures how often readers chose a human author.
- Made by
- Skills IL
- Released
- October 2026
- Kind
- Chat and instructions in many languages
- Level
- Everyday
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- Hebrew
- Interaction
- Single turn
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- A host
- In views
- Kept fresh
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Gemini 1.0 Pro leads with 44.3% among models released by October 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in October 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 11 more
- 1
Gemini 1.0 Pro 44.3%
- 2 Claude Fable 5.1 44.3%
- 3
Llama 4 Maverick 44%
- 4 Claude Opus 5.5 42.7%
- 5
Qwen 3.8 Max 42.1%
- 6 GPT-6 Astra 40.6%
- 7
Gemini 3.8 Flash 40.2%
- 8
Mistral Large 4 37.7%
- 9 Grok 4.7 37.6%
- 10 GPT-6.1 Sol 37.2%
- 11 Claude Sonnet 5.5 35.8%
- 12
DeepSeek-V4-Pro 35.5%
- 13 GLM-5.3 34.2%
- 14 Kimi K3 31.4%
Source: Official Human or AI? (Skills IL) leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 44.3% 38 to 51 | Dec 2023 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 44.3% 38 to 51 | Sep 2026 | Official leaderboard | |
| 3 | | 44% 38 to 51 | Apr 2025 | Official leaderboard | |
| 4 | Claude Opus 5.5 | 42.7% 36 to 50 | Sep 2026 | Official leaderboard | |
| 5 | | 42.1% ±7 | Aug 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 40.6% 34 to 47 | Sep 2026 | Official leaderboard | |
| 7 | | 40.2% 34 to 47 | Sep 2026 | Official leaderboard | |
| 8 | | 37.7% 31 to 45 | Oct 2026 | Official leaderboard | |
| 9 | Grok 4.7 | 37.6% ±6.5 | Sep 2026 | Official leaderboard | |
| 10 | GPT-6.1 Sol | 37.2% 31 to 44 | Sep 2026 | Official leaderboard | |
| 11 | Claude Sonnet 5.5 | 35.8% 30 to 43 | Sep 2026 | Official leaderboard | |
| 12 | | 35.5% 30 to 42 | Apr 2026 | Official leaderboard | |
| 13 | GLM-5.3 | 34.2% 28 to 41 | Aug 2026 | Official leaderboard | |
| 14 | Kimi K3 | 31.4% 26 to 38 | Jul 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Human or AI? (Skills IL) 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 Human or AI? (Skills IL) 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
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (14 entries).
- Pass Models scored 14 models we track.
- Pass Newest score The newest is from October 2026, for Mistral Large 4.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 44.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on agentskills.co.il: 14 rows for models we track 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.