TOP 3D AI
Microsoft's 4B-parameter image-to-3D model producing up to 1536³ resolution PBR textured assets. Uses novel O-Voxel representation that handles arbitrary topology including open surfaces and non-manifold geometry. Generates high-fidelity assets in 3-60 seconds depending on resolution. Fully open source under MIT license.
Arena Rank
#11
Overall ELO
1008
Geometry ELO
1022
Win Rate
50%
Arena Votes
Total: 1,614 votes
Average Generation Cost
Free (limited)
Typical runtime: 1.0 min
Curated from neighboring ranks
#10 · 1020 ELO
TRELLIS.2 is ranked #11 (1008 ELO) while Prism v3.0 currently sits at #10 (1020 ELO).
Prism v3.0 holds a 12 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 50% of its judged matches overall, compared to 58% for Prism v3.0.
TRELLIS.2 also tends to finish generations faster (1.0 min vs 4.3 min).
#12 · 1008 ELO
TRELLIS.2 is ranked #11 (1008 ELO) while Hitem3D v1.0 currently sits at #12 (1008 ELO).
TRELLIS.2 maintains a 0 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 50% of its judged matches overall, compared to 54% for Hitem3D v1.0.
TRELLIS.2 also tends to finish generations faster (1.0 min vs 3.0 min).
#9 · 1025 ELO
TRELLIS.2 is ranked #11 (1008 ELO) while Tripo AI v3.0 currently sits at #9 (1025 ELO).
Tripo AI v3.0 holds a 17 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 50% of its judged matches overall, compared to 56% for Tripo AI v3.0.
TRELLIS.2 also tends to finish generations faster (1.0 min vs 4.0 min).
#13 · 1006 ELO
TRELLIS.2 is ranked #11 (1008 ELO) while Rodin Gen 1.5 currently sits at #13 (1006 ELO).
TRELLIS.2 maintains a 2 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 50% of its judged matches overall, compared to 45% for Rodin Gen 1.5.
TRELLIS.2 also tends to finish generations faster (1.0 min vs 2.5 min).
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #11 with an arena ELO of 1008. It has participated in 1,614 community votes so far.
How much does it cost to generate with TRELLIS.2?
TRELLIS.2 does not expose confirmed pricing data inside Arena mode yet, so costs vary by plan.
When should I choose TRELLIS.2 over Prism v3.0?
TRELLIS.2 is ranked #11 (1008 ELO) while Prism v3.0 currently sits at #10 (1020 ELO). Prism v3.0 holds a 12 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 50% of its judged matches overall, compared to 58% for Prism v3.0. TRELLIS.2 also tends to finish generations faster (1.0 min vs 4.3 min).
Follow TRELLIS (Microsoft) on X (Twitter) for the latest news, updates, and announcements.
Follow @MSFTResearch