Infra layer for physical RSI
Palo Alto, United States
Joined August 2026
- Tweets252
- Following666
- Followers645
- Likes316
Pinned Tweet
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 retweeted
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 retweeted
Now for the buildings behind the bars 👀
MiniMax M3.1 Flash 🆚 DeepSeek V4.1 Flash 1017 🆚 Opus 5.5—all at max effort.
Their overall BuildingBench scores: 73.3 🆚 81.9 🆚 86.8. MiniMax still has ground to cover, but this is an exciting start for an open model you can currently try for free.
Where do you see the biggest differences in geometry and detail?
buildingbench.enactra.ai/
Now for the buildings behind the bars 👀
MiniMax M3.1 Flash 🆚 DeepSeek V4.1 Flash 1017 🆚 Opus 5.5—all at max effort.
Their overall BuildingBench scores: 73.3 🆚 81.9 🆚 86.8. MiniMax still has ground to cover, but this is an exciting start for an open model you can currently try for free.
Where do you see the biggest differences in geometry and detail?
buildingbench.enactra.ai/
Enactra AI retweeted
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 🔥
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 retweeted
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 retweeted
💥炸了！DeepSeek V4.1 Flash 1017 直接杀进 BuildingBench 3D 建筑重建 Top 5！开源模型把前沿闭源打得有点懵 ！
🔹DeepSeek 1017：81.9 分，$3.01/任务
🔹Claude Fable 5.1：81.4 分，成本约 11 倍
🔹Gemini 4 Argon：81.2 分，成本约 2 倍
🔹Claude Sonnet 5.5：82.1 分，成本约 15 倍
🔹Grok 4.7：78.3 分，成本约 4 倍
从真实照片反向重建 3D 建筑，上一代 72.9 → 81.9（+9 分），开源直接贴上甚至超越 Fable / Argon 级别，成本却是它们的零头。
梁文峰真的在把 3D 空间推理的门槛砸下来了
开源权重 + 极致性价比，这才是真正的“性能-成本”帕累托前沿。
#DeepSeek #DeepSeekV41 #BuildingBench #3DGeneration #OpenSourceAI #AIBenchmark #梁文峰 #梁圣
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 retweeted
Big win for open models!
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 🔥
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.
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 🔥
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 🔥
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 retweeted
Check out all simulated buildings by all models here
enactra.ai/buildingbench/
🎉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 retweeted
Huge leap with world box!
🚨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. 🧵
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 💎
🚨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. 🧵
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.
🚨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. 🧵
Enactra AI retweeted
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. 🧵