Citable dataset
Open Source LLM Statistics (2026)
Updated August 15, 2026 · Auto-generated from BenchLM's live dataset on every data refresh
As of August 15, 2026, 9 of the top 50 AI models on BenchLM (18%) are open-weight.
Key statistics
- As of August 15, 2026, 9 of the top 50 AI models on BenchLM (18%) are open-weight.
- As of August 15, 2026, the highest-ranked open-weight model on BenchLM is Alibaba's Qwen3.8 Max at 79.91/100 and #6 overall.
- As of August 15, 2026, 96 open-weight models receive a current overall score in BenchLM's ranked cohort.
- The gap between the top proprietary model (Claude Mythos 5) and the top open-weight model (Qwen3.8 Max) is 3.3 points on BenchLM's 100-point overall score as of August 15, 2026.
- 52% of the 394 AI models tracked by BenchLM (206 models) are open-weight as of August 15, 2026.
- The Arena Elo gap between the top closed and top open model narrowed to 37.7 points by 2026-07-21, from 43 points roughly a year earlier, per Arena data tracked on BenchLM.
As of August 15, 2026, the highest-ranked open-weight model on BenchLM is Alibaba's Qwen3.8 Max at 79.91/100 and #6 overall.
Qwen3.8 Max (79.91/100)
As of August 15, 2026, 96 open-weight models receive a current overall score in BenchLM's ranked cohort.
96 models
The gap between the top proprietary model (Claude Mythos 5) and the top open-weight model (Qwen3.8 Max) is 3.3 points on BenchLM's 100-point overall score as of August 15, 2026.
3.3 points
Methodology & sources
"Open-weight" follows the sourceType field in BenchLM's catalog. Rankings use the frozen BenchAlign v5 overall score and keep Supported separate from Estimated evidence. Arena Elo figures come from the Arena leaderboard snapshot tracked on BenchLM.
Cite these statistics
Every number on this page is generated from BenchLM's live dataset and refreshed with each data update. Link any statistic directly using its anchor, or cite the page as:
BenchLM.ai, "LLM Statistics" (August 15, 2026), https://benchlm.ai/stats/open-source-llmFrequently Asked Questions
How close are open-source models to closed models?
As of August 15, 2026, the top open-weight model (Qwen3.8 Max) ranks #6 overall on BenchLM, 3.3 points behind the top proprietary model (Claude Mythos 5) on a 100-point scale.
What share of top AI models are open-weight?
18% of BenchLM's overall top 50 (9 models) are open-weight as of August 15, 2026.
What is the best open-source LLM by benchmark score?
As of August 15, 2026, Alibaba's Qwen3.8 Max is the highest-ranked open-weight model on BenchLM at 79.91/100 and #6 overall. “Open-weight” describes downloadable weights; the page separates OSI-approved licenses from community and custom terms.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.