
4th yr undergrad @UChicago (CS and philosophy), RA @ChicagoHAI and @BerkeleySky, RL env @bespokelabsai
- Tweets111
- Following436
- Followers157
- Likes262

ALT The leaderboard of MAC Bench: one bar per model shows the score of a single agent and the gain from more agents. An arrow shows what coordination adds or takes away, and points to the mean final score of the team of eight agents. Opus 5.5 scores 0.534, with a green arrow to the right for a gain from coordination. GPT-6.1 Sol scores 0.406 and Gemini 4 Argon 0.319, each with a red arrow back to the left for a loss from coordination.

ALT The leaderboard of MAC Bench: one bar per model shows the score of a single agent and the gain from more agents. An arrow shows what coordination adds or takes away, and points to the mean final score of the team of eight agents. Opus 5.5 scores 0.534, with a green arrow to the right for a gain from coordination. GPT-6.1 Sol scores 0.406 and Gemini 4 Argon 0.319, each with a red arrow back to the left for a loss from coordination.

ALT The leaderboard of MAC Bench: one bar per model shows the score of a single agent and the gain from more agents. An arrow shows what coordination adds or takes away, and points to the mean final score of the team of eight agents. Opus 5.5 scores 0.534, with a green arrow to the right for a gain from coordination. GPT-6.1 Sol scores 0.406 and Gemini 4 Argon 0.319, each with a red arrow back to the left for a loss from coordination.























