Knowledge · Benchmark profile
A display-only Artificial Analysis model-openness index.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on Artificial Analysis Openness Index
Nemotron 3 Ultra leads at 83.3 index, followed by DeepSeek V4 Flash (Max) (50 index) and DeepSeek V4 Pro (Max) (50 index).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
10 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Nemotron 3 Ultra | #1 | NVIDIA | 83.3 index |
| DeepSeek V4 Flash (Max) | #2 | DeepSeek | 50 index |
| DeepSeek V4 Pro (Max) | #3 | DeepSeek | 50 index |
| GLM-5.2 | #4 | Z.AI | 44.4 index |
| Command A+ | #5 | Cohere | 38.9 index |
| Gemma 4 31B | #6 | 38.9 index | |
| GPT-OSS 120B | #7 | OpenAI | 38.9 index |
| MiMo-V2.5-Pro | #8 | Xiaomi | 38.9 index |
| MiniMax M3 | #9 | MiniMax | 33.3 index |
| Mistral Medium 3.5 128B | #10 | Mistral AI | 33.3 index |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Nemotron 3 Ultra nemotron-3-ultra-550b | NVIDIA | open | Estimated reference | 83.3 index |
| #2 | DeepSeek V4 Flash (Max) deepseek-v4-flash-max | DeepSeek | open | Estimated reference | 50 index |
| #3 | DeepSeek V4 Pro (Max) deepseek-v4-pro-max | DeepSeek | open | Estimated reference | 50 index |
| #4 | GLM-5.2 glm-5-2 | Z.AI | open | Estimated reference | 44.4 index |
| #5 | Command A+ command-a-plus | Cohere | open | Estimated reference | 38.9 index |
| #6 | Gemma 4 31B gemma-4-31b | open | Reference only | 38.9 index | |
| #7 | GPT-OSS 120B gpt-oss-120b | OpenAI | open | Reference only | 38.9 index |
| #8 | MiMo-V2.5-Pro mimo-v2-5-pro | Xiaomi | closed | Reference only | 38.9 index |
| #9 | MiniMax M3 MiniMax-M3 | MiniMax | — | Reference only | 33.3 index |
| #10 | Mistral Medium 3.5 128B mistral-medium-3-5-128b | Mistral AI | open | Estimated reference | 33.3 index |
The top of this snapshot is led by Nemotron 3 Ultra at 83.3 index; third place is 33.3 points behind. The top-10 spread is 50.0 points.
About Artificial Analysis Openness Index
A display-only Artificial Analysis model-openness index. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A display-only Artificial Analysis model-openness index.
Nemotron 3 Ultra by NVIDIA currently leads with 83.3 index.
10 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
2026 · 4 results · Reference
Massive Multitask Language Understanding2020 · 8 results · Reference
Graduate-Level Google-Proof Q&A2023 · 70 results · Reference
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines2025 · 19 results · Reference
Massive Multitask Language Understanding Professional2024 · 42 results · Reference
AGIEval2026 · 3 results · Reference
