Surface Evolver Bench Leaderboard
Surface Evolver Bench tests whether a model can write a correct simulation file for Surface Evolver, a physics tool that models surfaces shaped by tension, gravity and volume constraints, defining a 3D structure in its domain-specific format from only a few examples. Scores compare the resulting geometry — volume, area and energy — against reference solutions; the benchmark was built by an independent developer (GitHub: yhenon).
Source: epoch15 open models ranked+13 proprietaryData through Oct 2026
Open models ranked on Surface Evolver Bench
# shows rank among open models / rank overall (including proprietary).
| # | Model | Score | VRAM @ Q4 |
|---|---|---|---|
| 1 / 2 | Kimi K3 · 2779.9B | 95.0% | ~1674 GB |
| 2 / 14 | GLM 5.2 · 753.3B | 55.6% | ~456 GB |
| 3 / 15 | MiniMax M3 · 427.0B | 55.0% | ~257 GB |
| 4 / 16 | GLM 5.3 Flash · 321.3B | 52.5% | ~195 GB |
| 5 / 18 | Kimi K2.7 Code · 1026.9B | 48.8% | ~620 GB |
| 6 / 19 | DeepSeek V4.1 Flash · 763.2B | 46.3% | ~458 GB |
| 7 / 20 | Qwen3.8 27B · 27.8B | 45.0% | ~17 GB |
| 8 / 21 | Qwen3.6 35B A3B · 36.0B | 44.4% | ~22 GB |
| 9 / 22 | DeepSeek V4 Pro · 1598.8B | 40.0% | ~960 GB |
| 10 / 23 | Gemma 4 31B IT · 31.3B | 30.6% | ~20 GB |
| 11 / 24 | Mistral Large 4 1T A52B · 1000B | 28.1% | ~604 GB |
| 12 / 25 | Mistral Medium 3.5 128B · 127.7B | 26.9% | ~78 GB |
| 13 / 26 | GPT OSS 120B · 116.8B | 25.0% | ~71 GB |
| 14 / 27 | Laguna M.1 · 225.8B | 15.6% | ~136 GB |
| 15 / 28 | Trinity Large Thinking · 398.6B | 15.6% | ~798 GB |
Score vs model size
Which models give the most quality for their size — the ones worth running locally.
- Qwen3.8 27B, 28B, score 45.0% — on the efficiency frontier (best score at its size or smaller).
- GLM 5.3 Flash, 321B, score 52.5% — on the efficiency frontier (best score at its size or smaller).
- MiniMax M3, 427B, score 55.0% — on the efficiency frontier (best score at its size or smaller).
- GLM 5.2, 753B, score 55.6% — on the efficiency frontier (best score at its size or smaller).
- Kimi K3, 2.8T, score 95.0% — on the efficiency frontier (best score at its size or smaller).
Surface Evolver Bench: frequently asked questions
- What is the best open LLM on Surface Evolver Bench?
- Kimi K3 is the top open model on Surface Evolver Bench, scoring 95.0%. Among all models tested — including proprietary ones — it ranks #1. That puts it ahead of every proprietary model we track, including Claude Fable 5 (high) (Anthropic) at 95.0%.
- What's the best Surface Evolver Bench model you can run on a 24 GB GPU?
- Qwen3.8 27B is the highest-scoring open model that fits in 24 GB at 4-bit quantization (~17 GB), scoring 45.0% on Surface Evolver Bench.
- Can open models match proprietary models on Surface Evolver Bench?
- Yes — the best open model (Kimi K3, 95.0%) matches or beats every proprietary model we track on Surface Evolver Bench.
Scores aggregated from epoch. llmrun does not run this benchmark — see the source for methodology, or the about benchmarks for what it measures.