Best open-weight LLM for general-purpose work
- models ranked
- 11
- downloads of #1, 30 days
- 42.1K
- lead over #2
- +1.5 pts
Vals Index · read October 21
- New DeepSeek V4.1 Flash 1017 October 17
- New E Glimpse October 17
- New Mercury 3 October 16
- New R Beam 1.0 501B A23B October 16
As of October 21, 2026, DeepSeek V4.1 Flash 1017 leads 11 open-weight models on Vals Index with 61.3%, ahead of Z.ai GLM 5.3 (59.7%) and Xiaomi MiMo-V2.6-Pro (57.8%).
The full best LLM for general use ranking combines this benchmark with others.
| Rank | Model | Vals Index | Coding evidence | Weights | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash 1017 DeepSeek | 61.3% | deepseek-ai/DeepSeek-V4.1-Flash-1017 | 70.3 | $0.60 | |
| 2 | GLM 5.3 Z.ai | 59.7% | zai-org/GLM-5.3 | 70.6 | $4.40 | |
| 3 | MiMo-V2.6-Pro Xiaomi | 57.8% | XiaomiMiMo/MiMo-V2.6-Pro-RL | 65.4 | $0.87 | |
| 4 | MiMo-V2.6-Flash Xiaomi | 54.8% | XiaomiMiMo/MiMo-V2.6-Flash-RL | 54.7 | $0.28 | |
| 5 | Hy4 preview Tencent | 53.2% | tencent/Hy4-preview | 44.3 | $2.2509 | |
| 6 | DeepSeek V4 Pro 0813 DeepSeek | 53.0% | deepseek-ai/DeepSeek-V4-Pro-0813 | 56.1 | $1.98 | |
| 7 | Kimi K3 Moonshot AI | 53.0% | moonshotai/Kimi-K3 | 62.3 | $15.00 | |
| 8 | GLM 5.3 Flash Z.ai | 50.9% | zai-org/GLM-5.3-Flash | 57.7 | $0.50 | |
| 9 | Muse Spark Open Meta | 48.6% | meta-models/Muse-Spark-Open-816B-A42B | 47.4 | $4.25 | |
| 10 | T Inkling Thinking Machines | 29.0% | thinkingmachines/Inkling | 31.5 | $4.05 | |
| 11 | T Inkling Small Thinking Machines | 27.6% | thinkingmachines/Inkling-Small | 27.3 | $1.20 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models on the Vals Index board that OpenRouter links to a public Hugging Face repository, by their Vals Index result. We do not check the license; read it on the repository page.
- OpenRouter, fetched
- Vals Index, fetched , board updated October 21, 2026