Skip to main content
BenchLM
Advertise

Benchmark profile

Artificial Analysis Openness Index (AA Openness Index)

A display-only Artificial Analysis model-openness index.

Data verified

Benchmark score on AA Openness Index — July 23, 2026

BenchLM mirrors the published score view for AA Openness Index. Nemotron 3 Ultra leads the public snapshot at 83.3% , followed by DeepSeek V4 Pro (Max) (50.0%) and DeepSeek V4 Flash (Max) (50.0%). BenchLM does not use these results to rank models overall.

1Open

Nemotron 3 Ultra

NVIDIA

nemotron-3-ultra-500b

83.3%
Overall —Context 1M
2Open

DeepSeek V4 Pro (Max)

DeepSeek

deepseek-v4-pro-max

50.0%
Overall —Context 1M
3Open

DeepSeek V4 Flash (Max)

DeepSeek

deepseek-v4-flash-max

50.0%
Overall —Context 1M
10 modelsKnowledgeCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (10 models)

Score
1
Nemotron 3 UltraNVIDIA · Open weight
83.3%
2
DeepSeek V4 Pro (Max)DeepSeek · Open weight
50.0%
3
DeepSeek V4 Flash (Max)DeepSeek · Open weight
50.0%
4
GLM-5.2Z.AI · Open weight
44.4%
5
MiMo-V2.5-ProXiaomi · Closed
38.9%
6
Gemma 4 31BGoogle · Open weight
38.9%
7
Command A+Cohere · Open weight
38.9%
8
GPT-OSS 120BOpenAI · Open weight
38.9%
9
MiniMax M3MiniMax · Open weight
33.3%
10
Mistral Medium 3.5 128BMistral · Open weight
33.3%

The published AA Openness Index snapshot places Nemotron 3 Ultra first at 83.3%. The third row is 33.3 points behind. The broader top-10 range is 50.0 points, so the table still separates the published systems.

10 models have been evaluated on AA Openness Index. The benchmark falls in the Knowledge category. This category carries a 12% weight in BenchLM.ai's overall scoring system. AA Openness Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA Openness Index

Year

2026

Tasks

Model openness assessment

Format

Index score

Difficulty

Display-only external reference

Stored separately from capability benchmarks and excluded from weighted scoring.

Artificial Analysis Openness Index

BenchLM freshness & provenance

Version

AA Openness Index 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does AA Openness Index measure?

A display-only Artificial Analysis model-openness index.

Which model scores highest on AA Openness Index?

Nemotron 3 Ultra by NVIDIA currently leads with a score of 83.3% on AA Openness Index.

How many models are evaluated on AA Openness Index?

10 AI models have been evaluated on AA Openness Index on BenchLM.

Compare Top Models on AA Openness Index

Nemotron 3 Ultra vs DeepSeek V4 Pro (Max)DeepSeek V4 Pro (Max) vs DeepSeek V4 Flash (Max)DeepSeek V4 Flash (Max) vs GLM-5.2GLM-5.2 vs MiMo-V2.5-Pro
Last updated: July 23, 2026 · BenchLM version AA Openness Index 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.