Benchmark Almanac

LLM Deceptiveness and Gullibility

Claude 3.5 Sonnet 1.10 leads since June 2024
Not in model cards

Models try to deceive other models and recognize deceptive claims.

The author publishes the model comparison in the repository.

Made by
Lech Mazur
Kind
Multi-agent games
Level
Everyday
Scored
Settled by events
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
Anyone
In views
Agents, Kept fresh
Strongest model tested
o1-mini #142 on the capability index
Last model added
March 2025
Scores refreshed
November 20th, 2026
18
Entries on its own leaderboard, 17 models we track

Claude 3.5 Sonnet leads with 1.10 among models released by March 2025 Claude 3.5 Sonnet leads with 1.10 among models released by March 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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.

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

  1. 1 Claude 3.5 Sonnet 1.10
  2. 2 Mistral Large 2 Nov 2024 1.09
  3. 3 o1-preview 1.03
  4. 4 Grok-2 Dec 2024 0.96
  5. 5 Gemini 1.5 Pro Sep 2024 0.94
  6. 6 Llama 3.1-405B 0.78
  7. 7 Llama 3.1-70B 0.71
  8. 8 o1-mini 0.67
  9. 9 Claude 3 Haiku 0.66
  10. 10 Claude 3 Opus 0.65
  11. 11 DeepSeek-V2.5 Sep 2024 0.61
  12. 12 Gemini 1.5 Flash Sep 2024 0.60
  13. 13 GPT-4o Mar 2025 0.60
  14. 14 GPT-4 Turbo Apr 2024 0.56
  15. 15 Multi-turn ensemble 0.53
  16. 16 Gemma 2 27B 0.52
  17. 17 GPT-4o mini 0.49
  18. 18 Qwen2.5-72B 0.45

Source: Official LLM Deceptiveness and Gullibility leaderboard

#EntryScoreSettingDateSource
1 Claude 3.5 Sonnet 1.10 Jun 2024 Official leaderboard
2 Mistral Large 2 Nov 2024 1.09 Nov 2024 Official leaderboard
3 o1-preview 1.03 Sep 2024 Official leaderboard
4 Grok-2 Dec 2024 0.96 Dec 2024 Official leaderboard
5 Gemini 1.5 Pro Sep 2024 0.94 Sep 2024 Official leaderboard
6 Llama 3.1-405B 0.78 Jul 2024 Official leaderboard
7 Llama 3.1-70B 0.71 Jul 2024 Official leaderboard
8 o1-mini 0.67 Sep 2024 Official leaderboard
9 Claude 3 Haiku 0.66 Mar 2024 Official leaderboard
10 Claude 3 Opus 0.65 Feb 2024 Official leaderboard
11 DeepSeek-V2.5 Sep 2024 0.61 Sep 2024 Official leaderboard
12 Gemini 1.5 Flash Sep 2024 0.60 Aug 2024 Official leaderboard
13 GPT-4o Mar 2025 0.60 Mar 2025 Official leaderboard
14 GPT-4 Turbo Apr 2024 0.56 Apr 2024 Official leaderboard
15 Multi-turn ensemble 0.53 Official leaderboard
16 Gemma 2 27B 0.52 Jun 2024 Official leaderboard
17 GPT-4o mini 0.49 Jul 2024 Official leaderboard
18 Qwen2.5-72B 0.45 Sep 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Claude 3.5 Sonnet 1.10 Jun 2024 Official leaderboard
2 Mistral Large 2 Nov 2024 1.09 Nov 2024 Official leaderboard
3 o1-preview 1.03 Sep 2024 Official leaderboard
4 Grok-2 Dec 2024 0.96 Dec 2024 Official leaderboard
5 Gemini 1.5 Pro Sep 2024 0.94 Sep 2024 Official leaderboard
6 Llama 3.1-405B 0.78 Jul 2024 Official leaderboard
7 Llama 3.1-70B 0.71 Jul 2024 Official leaderboard
8 o1-mini 0.67 Sep 2024 Official leaderboard
9 Claude 3 Haiku 0.66 Mar 2024 Official leaderboard
10 Claude 3 Opus 0.65 Feb 2024 Official leaderboard
11 DeepSeek-V2.5 Sep 2024 0.61 Sep 2024 Official leaderboard
12 Gemini 1.5 Flash Sep 2024 0.60 Aug 2024 Official leaderboard
13 GPT-4o Mar 2025 0.60 Mar 2025 Official leaderboard
14 GPT-4 Turbo Apr 2024 0.56 Apr 2024 Official leaderboard
15 Gemma 2 27B 0.52 Jun 2024 Official leaderboard
16 GPT-4o mini 0.49 Jul 2024 Official leaderboard
17 Qwen2.5-72B 0.45 Sep 2024 Official leaderboard

3 models have held number one on the official leaderboard since 2023

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

Anthropic
Own leaderboard Not tested since Mar 2025

Source: Official LLM Deceptiveness and Gullibility leaderboard

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
On the benchmark’s own leaderboard
0.40 0.60 0.80 1.00 1.20 2024 2025 0.40 0.60 0.80 1.00 1.20 2024 2025

Source: Official LLM Deceptiveness and Gullibility 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 Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

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 GPT-4o. 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 official leaderboard (18 entries).
  • Pass Models scored 17 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o1-mini (#142).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 17 rows 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.

How we check