←
Maitrix.org277 posts
Maitrix.org avatar

Maitrix.org

@MaitrixOrg

Open Organization to Build AI-powered Realities with LLMs, World Models, Agent Models.

◷ Joined March 2024▧ 28 Photos and videos
Maitrix.org avatar
Maitrix.org@MaitrixOrg·Oct 15

Wow… jumping from 23 gems to 61 on MazeBench is definitely mind-blowing 🤯🤯

🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning. Astra: 23 gems 💎💎 Astra+WorldBox: 61 gems 💎💎💎💎💎 MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems. WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning. Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵

0:52
Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 23

Wow! Kimi K3.1 Pro leaps into BuildingBench’s top six! Another open model making serious strides in 3D 🏗️🔥 🎈54.0 → 81.6 from Kimi K3—a massive 27.6-point jump! 🎈Essentially matches DeepSeek V4.1 Flash 1017’s 81.9, joining the cluster around Sonnet 5.5 and Fable 5.1. 🎈Estimated median cost: $12.58/task. Cheaper than Sonnet and Fable, though DeepSeek remains more cost-efficient at $3.01. The reconstruction shown here scores 90.8: Melbourne’s Australian Centre for Contemporary Art, rebuilt from photographs. Exciting to see more open models reaching this level of spatial reasonin!

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 19

MiniMax M3.1 Flash reshapes BuildingBench’s cost–quality frontier! Another open model making moves in 3D 🏗️🔥 🎈 73.3 overall, ranking #12. 🎈 Above SWE-2’s 67.3, taking its place on the Pareto frontier. 🎈 Close to the previous DeepSeek V4.1 Flash’s 72.9—and currently free through OpenRouter! Its best reconstruction hits 88.8 on Melbourne’s Australian Centre for Contemporary Art. How does it look alongside DeepSeek V4.1 Flash 1017 and #1 Opus 5.5? Comparison video below 👇

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 18

See DeepSeek’s 3D leap with your own eyes 👀🏗️ DeepSeek V4.1 Flash 1017 🆚 DS V4.1 Flash 🆚 GPT-6 Astra: three buildings, side by side. The new open model improves on 11 of 12 buildings in BuildingBench, jumping from 72.9 → 81.9—closing in on Astra’s 84.3 at less than half the median cost ($3.01 vs $7.05/task). Open models are getting seriously good at building worlds 🔥

0:08

Wow🙀🙀 DeepSeek V4.1 Flash 1017 joins BuildingBench’s top five—an exciting leap for open models!! 🔥 We tested its 3D building reconstruction from real photos. An open model delivering this level of spatial reasoning at this cost is exciting to see! 👀 🎈 81.9 overall, up from 72.9 for the previous version. A 9-point jump! 🎈 Slightly higher than Fable 5.1’s 81.4, and essentially level with Sonnet 5.5’s 82.1. 🎈 Estimated median cost: $3.01/task. About 1/11 of Fable 5.1’s cost and 1/15 of Sonnet 5.5’s.

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 18

Wow🙀🙀 DeepSeek V4.1 Flash 1017 joins BuildingBench’s top five—an exciting leap for open models!! 🔥 We tested its 3D building reconstruction from real photos. An open model delivering this level of spatial reasoning at this cost is exciting to see! 👀 🎈 81.9 overall, up from 72.9 for the previous version. A 9-point jump! 🎈 Slightly higher than Fable 5.1’s 81.4, and essentially level with Sonnet 5.5’s 82.1. 🎈 Estimated median cost: $3.01/task. About 1/11 of Fable 5.1’s cost and 1/15 of Sonnet 5.5’s.

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 16

🎉Excited to see two new US open models from this week: 📘Meta’s Muse Spark Open 📗NVIDIA’s Nemotron 3.5 Super VL How well can they build in 3D? 🏗️👀 We tested both on BuildingBench: reconstructing real buildings from photographs. 📘Muse Spark Open (max): 56.9 at an estimated $8.59/task—comparable to Kimi K3’s 54.0. 📗 Nemotron 3.5 Super VL (max): 37.8 at an estimated $0.76/task—among the cheapest tested, with performance near GLM-5.3 Flash’s 33.0. DeepSeek V4.1 Flash remains well ahead of both: 72.9 at an estimated $2.33/task. GLM-5.3 FlashX also scores higher, at 68.0. Neither newcomer reaches the cost–quality frontier. More open models to choose from, and plenty of room to improve spatial reasoning! Both ran in Claude Code at max effort. Costs are estimated median per task.

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 15

The completed WorldBox run reaches 230 rooms and 61 gems at 35,000 actions using 973M tokens. It also reaches Astra’s 23-gem result in just 10,929 actions—roughly half as many.

Post attachmentPost attachmentPost attachment
Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 15

Not just mazes—WorldBox helps agents in Minecraft, too ⛏️ With WorldBox, Opus 5.5 reached more than twice the average progression tier of the base agent in our tests. Astra improved substantially, too. Spatial memory management and sandbox help agents remember where resources are—and put that knowledge to work. From chasing gems to mining diamonds 💎

0:31

🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning. Astra: 23 gems 💎💎 Astra+WorldBox: 61 gems 💎💎💎💎💎 MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems. WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning. Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵

0:52
Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 15

Watch how GPT‑6 Astra + WorldBox tackle MazeBench, from its first action to gem💎 #61—32,980 live actions and around 1B tokens. Building bridges with boxes, launching across gaps, solving puzzles that span multiple rooms… all while the map fills in. Remember, test, revise, repeat, and grab that gem. WorldBox offers the supporting layer for Astra.

2:37

🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning. Astra: 23 gems 💎💎 Astra+WorldBox: 61 gems 💎💎💎💎💎 MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems. WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning. Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵

0:52
Lianhui Qin avatar
⟳ Maitrix.org retweeted
Lianhui Qin@Lianhuiq·Oct 15

Long-horizon spatial reasoning remains a major challenge, even for the strongest frontier AI models. Impressive results from @EnactraAI! 🚀 WorldBox boosts GPT-6 Astra from 23 to 61 gems on MazeBench, a 2.7× improvement! Exciting to see how memory, world modeling, and simulation can help AI agents tackle much harder problems.

🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning. Astra: 23 gems 💎💎 Astra+WorldBox: 61 gems 💎💎💎💎💎 MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems. WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning. Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵

0:52
Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 15

🚨New level unlocked! 🚨 We doubled GPT‑6 Astra’s score on MazeBench with WorldBox, our agentic sandbox for spatial reasoning. Astra: 23 gems 💎💎 Astra+WorldBox: 61 gems 💎💎💎💎💎 MazeBench, by @patience_cave, is a tough test of long-horizon spatial reasoning: 256 interconnected rooms where even Opus 5.5 used 2.2B tokens and collected just 13 of 100 gems. WorldBox provides agents with an agentic sandbox, for managing long-term memory, inferring complex mechanics, and simulating reasoning. Watch the sandbox take shape and the agent tackle increasingly tricky puzzles. 🧵

0:52
Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 14

Gemini 4 Argon makes a big leap in 3D reconstruction 🏗️🚀 On BuildingBench, Argon (high) scores 81.2—up from Gemini 3.8 Flash’s 54.8, placing #6 among all 30 models. Near Fable 5.1 quality at ~1/5 the cost. Near Sonnet 5.5 quality at ~1/7. 👀 💸 Estimated median cost: $6.52 per building 🎨 Appearance score: 94.1, the third-highest 🏛️ Best reconstruction: Royal Exhibition Building, scoring 92.1 It doesn’t move the Pareto frontier: GPT‑6.1 Sol still scores higher at lower cost. But this is a substantial step forward for Gemini. Congrats @GeminiApp team!

The moment you've been waiting 4… Our new frontier model, Gemini 4 Argon, is rolling out now in the Gemini app to bring your most complex ideas into reality. See how Gemini 4 Argon and our latest updates across the Gemini app help you get the most out of every prompt. 🧵

Enactra AI avatar
⟳ Maitrix.org retweeted
Enactra AI@EnactraAI·Oct 13

Muse Wonder takes on #buildingbench 🏗️👀 How well can it turn photographs into 3D buildings? Muse Wonder (max) scores 70.3, ranking #12 of 31—roughly level with GPT‑6 Sol. Compared with Muse Spark 1.3: 📈 Score: 68.2 → 70.3 💸 Median cost per building: $5.89 → ~$7.72 📐 Higher geometry and surface scores, but lower appearance scores. A modest gain within statistical uncertainty. The Pareto frontier stays unchanged. Watch its best reconstruction: Helsinki’s Pikkuparlamentti, scoring 81.6 👇

with muse wonder, we aimed to build a model that is useful for real world tasks for real people, informed by our product adoption and how people use muse. we focused on things that might not look as glamorous on twitter (for example, not 3d demo games), which in retrospect we probably could have done more of.

Lianhui Qin avatar
⟳ Maitrix.org retweeted
Lianhui Qin@Lianhuiq·Oct 12

94.1% task success. Only 0.7% safe success. 🚨 AI agents can finish the job, but crash along the way. Introducing RT-SAFE: The physical world doesn't pause while agents think. Real-time evaluation exposes 12.3× more dangerous collisions than paused-world tests.

1:00