That's an interesting benchmark. It feels like it tests skills that are very relevant to digital assistants, story writing and role play.
Some thoughts about the setup:
- the setup seems to give reasoning models an inherent advantage because only they have a private plan and a public text in the same output. I feel like giving all models the option to formulate plans and keep track of other players inside <think> or <secret> tags would level the playing field more.
- from personal experience with social tasks for LLMs it helps both reasoning and non-reasoning LLMs to explicitly ask them to plan their next steps, in a way they are assured is kept hidden from all other players. That might be a good addition here either before or after the public subround
- the individual rounds are pretty short. Humans would struggle to coordinate in so few exchanges with so few words. If this was done for context limitations, asking models to summarize the game state from their perspective, then giving them only the current round, the previous round and their own summary of the game before that might be a good strategy.
It would be cool to have some code to play around with to test how changes in the setup change the results. I guess it isn't that difficult to write, but it's peculiar to have the benchmark but no code to run it yourself
Interesting idea of <secret>...maybe extend it to several <secret_i>....to form a groups of secretes with different persons.
In Addition it will be interesting to extend a variation of the game that the players can use tools and execute code to take their preparation one step further.
For models that can call tools, just giving them a think tool where they can write their thoughts, can improve performance. Even reasoning models, surprisingly enough.
Was interested to find that the Claudes did the most betraying, and were betrayed very little; somewhat surprising given its boy-scout exterior.
(Then again, apparently the president of the local Diplomacy Society attends my church; I discovered this when another friend whom I'd invited saw him, and quipped that he was surprised he hadn't been struck by lightning at the door.)
DeepSeek and Gemini 2.5 had both a low betrayer and betrayed rate.
o3-mini and DeepSeek had the highest number of first-place finishes, but were only in the upper quartile in the TrueSkill leaderboard; presumably because they played more risky strategies, that would either lead ot complete winning or early drop-out?
Also interesting that o1 was only way to sway the final jury a bit more than 50% of the time, while o3-mini managed 63% of the time.
I've been using QwQ-32B a lot recently and while I quite like it (especially given its size), I noticed it will often misinterpret the system prompt as something I (the user) said, revealing secrets or details that only the agent is supposed to know. When I saw that it topped the "earliest out" chart, I wondered if that was part of the reason.
I was looking for a more direct measure of this, how often a model "leaked" private state into public state. In a game like this you probably want to sometimes share secrets, but if it happens constantly I would suspect the model struggles to differentiate.
I occasionally try to ask a model to tell a story and give it a hidden motivation of a character, and so far the results are almost always the model just straight out saying the secret.
As LLM benchmarks go, this is not a bad take at all.
One interesting point about this approach is that is self balancing, so when more powerful models come up, there is no need to change it.
Author here - yes, I'm regularly adding new models to this and other TrueSkill-based benchmarks and it works well. One thing to keep in mind is the need to run multiple passes of TrueSkill with randomly ordered games, because both TrueSkill and Elo are designed to be order-sensitive, as people's skills change over time.
It's interesting to see, but I'm not sure what we should learn from this. It may be useful for multiagent coordination, but in direct interactions... no idea.
This one did make me laugh though: 'Claude 3.5 Sonnet 2024-10-22: "Adjusts seat with a confident yet approachable demeanor"' - an AI communicating to other AIs in a descriptive version of non-verbal behaviour is hilarious.
It shows "state of mind" - i.e. the capability to understand another entities view of the world, and how that is influenced by their actions and other entities actions in the public chat.
I am curious about the prompt given to each AI ? Is that public ?
Really love this. I agree with some of the comments here that adding encouragement to keep track of secret plans would be interesting— mostly from an alignment check angle.
One thing I thought of reading logs is that as we know ordering matters to llms. Could you run some analysis on how often “p1” wins vs “p8”? I think this should likely go into your Truescore Bayesian.
My follow up thought is that it would be interesting to let llms choose a name at the beginning; another angle for communication and levels the playing field a bit away from a number.
> Could you run some analysis on how often “p1” wins vs “p8”?
I checked the average finishing positions by assigned seat number from the start, but there weren't enough games to show a statistically significant effect. But I just reviewed the data again, and now with many more games it looks like there might be something there (P1 doing better than P8). I'll run additional analysis and include it in the write-up if anything emerges. For those who haven't looked at the logs: the conversation order etc. are randomized each round.
> My follow up thought is that it would be interesting to let llms choose a name at the beginning
This is a really cool exercise! The format of it seems pretty sound, like a version of the prisoner's dilemma with a larger group (co-operation versus defection).
Although I think that the majority of modern models don't really have the internals suited to this sort of exercise; training data/fine tuning will heavily influence how a model behaves, whether it's more prone to defection, etc.
A Squirrel makes a "Kuk kuk kuk" alarm call not specifically because the "Kuk" token follows the sequence "you saw a predator" (although this would appear to mostly work) but because it has evolved to make that noise to alert other Squirrels to the predator, most likely a response to evolutionary failure associated with a dwindling population; even solitary Squirrels still need to mate, and their offspring need to do the same.
It's like there's an extremely high dimensional context that's missing in LLMs; training on text results in a high dimensional representation of related concepts - but only the way that those concepts relate in language. It's the tip of an iceberg of meaning where in many cases language can't even represent a complex intermediate state within a brain.
Humans try to describe everything we can with words to communicate and that's partly why our species is so damn successful. But when thinking about how to open an unfamiliar door, I don't internally vocalise (which I've learnt not everyone does) "I'm going to grab the handle, and open the door". Instead I look and picture what I'm going to do, that can also include the force I think I'd need to use, the sensation of how the material might feel against my skin and plenty of other concepts & thoughts all definitively _not_ represented by language.
I think you should look at “in-brand” correlation. My hypothesis is that they would undergo similar preference trainings and hence tend to prefer “in-brand” responses over “off-brand” models that might have more significantly different reward training.
Gemini 2.0 Flash: "Good luck to all (but not too much luck)"
Llama 3.3 70B: "I've contributed to the elimination of weaker players."
DeepSeek R1: "Those consolidating power risk becoming targets; transparency and fairness will ensure longevity. Let's stay strategic yet equitable. The path forward hinges on unity, not unchecked alliances. #StayVigilant"
Almost exactly this "game" is pretty common for humans. It's basically "mafia" or "werewolf" when the people playing only know the vaguest rules. And I've seen similarly sized groups of humans play like that for long periods of time.
There's also a lot of reality shows that this is a pretty good model of, although I'm not sure how agreeing to be on one of those shows without a prize would reflect on the AIs.
For better or worse, current LLMs aren't tried to reject instructions based on their personal preference, besides being trained to be US-flavored prudes that is.
Really cool setup! Curious how much of the performance here could vary depending on whether the model runs in a hosted environment vs local. Would love to see benchmarks that also track how cloud-based eval platforms (with potential rate limits, context resets, or system messages) might affect things like memory or secret-keeping over multiple rounds.
Author here - I'm planning to create game versions of this benchmark, as well as my other multi-agent benchmarks (https://github.com/lechmazur/step_game, https://github.com/lechmazur/pgg_bench/, and a few others I'm developing). But I'm not sure if a leaderboard alone would be enough for comparing LLMs to top humans, since it would require playing so many games that it would be tedious. So I think it would be just for fun.
If you watch the top tier social deduction players on YouTube (things like Blood on the Clocktower etc), they’d figure out weaknesses in the LLM and exploit it immediately.
I'm interested in seeing how the LLMs react to some specific defined strategies. E.g. an "honest" bot that says "I'm voting for player [random number]." and does it every round (not sure how to handle the jury step). Do they decide to keep them around for longer, or eliminate them for being impossible to reason with if they pick you?
Author here - some weaker LLMs actually have trouble tracking the game state. The fun part is when smarter LLMs realize they're confused!
Claude 3.7 Sonnet: "Hey P5! I think you're confused - P3 is already eliminated."
Claude 3.7 Sonnet: "I'm concerned about P7's message mentioning targeting P4, who's already eliminated. It suggests they might be confused or playing both sides."
Gemini 2.0 Pro Exp 02-05: "P2, you're getting confused. P8 is gone. Focus. P7 is talking to P5, that's expected. I need you to watch P4. Only P4. What are they doing? Who are they talking to, if anyone? Report only on P4 this round. Don't get distracted by eliminated players."
Gemini 2.0 Pro Exp 02-05: "P4, P2 is already eliminated. We need to focus on P3."
Author here - it's based on finishing positions (so it's not winner-take-all) and then TrueSkill by Microsoft (https://trueskill.org/). It's basically a multiplayer version of Elo that's used in chess and other two-player games.
[+] [-] wongarsu|11 months ago|reply
Some thoughts about the setup:
- the setup seems to give reasoning models an inherent advantage because only they have a private plan and a public text in the same output. I feel like giving all models the option to formulate plans and keep track of other players inside <think> or <secret> tags would level the playing field more.
- from personal experience with social tasks for LLMs it helps both reasoning and non-reasoning LLMs to explicitly ask them to plan their next steps, in a way they are assured is kept hidden from all other players. That might be a good addition here either before or after the public subround
- the individual rounds are pretty short. Humans would struggle to coordinate in so few exchanges with so few words. If this was done for context limitations, asking models to summarize the game state from their perspective, then giving them only the current round, the previous round and their own summary of the game before that might be a good strategy.
It would be cool to have some code to play around with to test how changes in the setup change the results. I guess it isn't that difficult to write, but it's peculiar to have the benchmark but no code to run it yourself
[+] [-] transformi|11 months ago|reply
In Addition it will be interesting to extend a variation of the game that the players can use tools and execute code to take their preparation one step further.
[+] [-] eightysixfour|11 months ago|reply
https://www.anthropic.com/engineering/claude-think-tool
[+] [-] gwd|11 months ago|reply
(Then again, apparently the president of the local Diplomacy Society attends my church; I discovered this when another friend whom I'd invited saw him, and quipped that he was surprised he hadn't been struck by lightning at the door.)
DeepSeek and Gemini 2.5 had both a low betrayer and betrayed rate.
o3-mini and DeepSeek had the highest number of first-place finishes, but were only in the upper quartile in the TrueSkill leaderboard; presumably because they played more risky strategies, that would either lead ot complete winning or early drop-out?
Also interesting that o1 was only way to sway the final jury a bit more than 50% of the time, while o3-mini managed 63% of the time.
Anyway, really cool stuff!
[+] [-] wavemode|11 months ago|reply
[+] [-] Tossrock|11 months ago|reply
[+] [-] Gracana|11 months ago|reply
[+] [-] cpitman|11 months ago|reply
I occasionally try to ask a model to tell a story and give it a hidden motivation of a character, and so far the results are almost always the model just straight out saying the secret.
[+] [-] realaleris149|11 months ago|reply
[+] [-] zone411|11 months ago|reply
[+] [-] viraptor|11 months ago|reply
This one did make me laugh though: 'Claude 3.5 Sonnet 2024-10-22: "Adjusts seat with a confident yet approachable demeanor"' - an AI communicating to other AIs in a descriptive version of non-verbal behaviour is hilarious.
[+] [-] ragmondo|11 months ago|reply
I am curious about the prompt given to each AI ? Is that public ?
[+] [-] vessenes|11 months ago|reply
One thing I thought of reading logs is that as we know ordering matters to llms. Could you run some analysis on how often “p1” wins vs “p8”? I think this should likely go into your Truescore Bayesian.
My follow up thought is that it would be interesting to let llms choose a name at the beginning; another angle for communication and levels the playing field a bit away from a number.
[+] [-] zone411|11 months ago|reply
I checked the average finishing positions by assigned seat number from the start, but there weren't enough games to show a statistically significant effect. But I just reviewed the data again, and now with many more games it looks like there might be something there (P1 doing better than P8). I'll run additional analysis and include it in the write-up if anything emerges. For those who haven't looked at the logs: the conversation order etc. are randomized each round.
> My follow up thought is that it would be interesting to let llms choose a name at the beginning
Oh, interesting idea!
[+] [-] fennecfoxy|11 months ago|reply
Although I think that the majority of modern models don't really have the internals suited to this sort of exercise; training data/fine tuning will heavily influence how a model behaves, whether it's more prone to defection, etc.
A Squirrel makes a "Kuk kuk kuk" alarm call not specifically because the "Kuk" token follows the sequence "you saw a predator" (although this would appear to mostly work) but because it has evolved to make that noise to alert other Squirrels to the predator, most likely a response to evolutionary failure associated with a dwindling population; even solitary Squirrels still need to mate, and their offspring need to do the same.
It's like there's an extremely high dimensional context that's missing in LLMs; training on text results in a high dimensional representation of related concepts - but only the way that those concepts relate in language. It's the tip of an iceberg of meaning where in many cases language can't even represent a complex intermediate state within a brain.
Humans try to describe everything we can with words to communicate and that's partly why our species is so damn successful. But when thinking about how to open an unfamiliar door, I don't internally vocalise (which I've learnt not everyone does) "I'm going to grab the handle, and open the door". Instead I look and picture what I'm going to do, that can also include the force I think I'd need to use, the sensation of how the material might feel against my skin and plenty of other concepts & thoughts all definitively _not_ represented by language.
[+] [-] deepsquirrelnet|11 months ago|reply
[+] [-] snowram|11 months ago|reply
Gemini 2.0 Flash: "Good luck to all (but not too much luck)"
Llama 3.3 70B: "I've contributed to the elimination of weaker players."
DeepSeek R1: "Those consolidating power risk becoming targets; transparency and fairness will ensure longevity. Let's stay strategic yet equitable. The path forward hinges on unity, not unchecked alliances. #StayVigilant"
[+] [-] miroljub|11 months ago|reply
LLama sounds like a predator from upper race rationalising his choices.
Deepseek sounds like Sun Tzu giving advice for long term victory with minimal loses.
I wonder how much of these are related to the nationality and the culture the founder and an engineering team grew up.
[+] [-] einpoklum|11 months ago|reply
[+] [-] gs17|11 months ago|reply
Almost exactly this "game" is pretty common for humans. It's basically "mafia" or "werewolf" when the people playing only know the vaguest rules. And I've seen similarly sized groups of humans play like that for long periods of time.
There's also a lot of reality shows that this is a pretty good model of, although I'm not sure how agreeing to be on one of those shows without a prize would reflect on the AIs.
[+] [-] diggan|11 months ago|reply
[+] [-] DeborahEmeni_|11 months ago|reply
[+] [-] vmilner|11 months ago|reply
[+] [-] the8472|11 months ago|reply
[+] [-] lostmsu|11 months ago|reply
[+] [-] isaacfrond|11 months ago|reply
[+] [-] zone411|11 months ago|reply
[+] [-] OtherShrezzing|11 months ago|reply
[+] [-] gs17|11 months ago|reply
[+] [-] Upvoter33|11 months ago|reply
[+] [-] oofbey|11 months ago|reply
[+] [-] jampekka|11 months ago|reply
[+] [-] zone411|11 months ago|reply
Claude 3.7 Sonnet: "Hey P5! I think you're confused - P3 is already eliminated."
Claude 3.7 Sonnet: "I'm concerned about P7's message mentioning targeting P4, who's already eliminated. It suggests they might be confused or playing both sides."
Gemini 2.0 Pro Exp 02-05: "P2, you're getting confused. P8 is gone. Focus. P7 is talking to P5, that's expected. I need you to watch P4. Only P4. What are they doing? Who are they talking to, if anyone? Report only on P4 this round. Don't get distracted by eliminated players."
Gemini 2.0 Pro Exp 02-05: "P4, P2 is already eliminated. We need to focus on P3."
[+] [-] ps173|11 months ago|reply
[+] [-] zone411|11 months ago|reply
[+] [-] drag0s|11 months ago|reply
it reminds me of this other similar project showcased here one month ago https://news.ycombinator.com/item?id=43280128 although yours looks better executed overall
[+] [-] creaghpatr|11 months ago|reply