Enter opens the highlighted result. Esc closes.

Best open-weight LLM for overall intelligence

MiMo-V2.6-Pro leads
46.3
models ranked
111
downloads of #1, 30 days
103.9K
lead over #2
+1.5

AA Intelligence Index · read October 22

  1. New DeepSeek V4.1 Flash 1017 October 17
  2. New E Glimpse October 17
  3. New Mercury 3 October 16
  4. New R Beam 1.0 501B A23B October 16

As of October 22, 2026, Xiaomi MiMo-V2.6-Pro leads 111 open-weight models on AA Intelligence Index with 46.3, ahead of Z.ai GLM 5.3 (44.8) and StepFun Step 5 Preview (43.7).

The full best LLM for overall intelligence ranking combines this benchmark with others.

Top 20 of 111, higher is better

Embed this data
Best open-weight LLM for overall intelligence
Rank Model AA Intelligence Index Coding evidence Weights Coding index Output $/Mtok
1
MiMo-V2.6-Pro Xiaomi
46.3
 XiaomiMiMo/MiMo-V2.6-Pro-RL 65.4 $0.87
2
GLM 5.3 Z.ai
44.8
 zai-org/GLM-5.3 70.6 $4.40
3
Step 5 Preview StepFun
43.7
 stepfun-ai/Step-5-Preview 61.1 $2.70
4
Kimi K3 Moonshot AI
43.6
 moonshotai/Kimi-K3 62.3 $15.00
5
GLM 5.3 Flash Z.ai
41.8
 zai-org/GLM-5.3-Flash 57.7 $0.50
6
Qwen3.8 2.4T A95B Qwen
39.9
 Qwen/Qwen3.8-2.4T-A95B Not benchmarked $6.00
7
DeepSeek V4.1 Flash 1017 DeepSeek
39.5
 deepseek-ai/DeepSeek-V4.1-Flash-1017 70.3 $0.60
8
MiMo-V2.6-Flash Xiaomi
37.9
 XiaomiMiMo/MiMo-V2.6-Flash-RL 54.7 $0.28
9
DeepSeek V4 Pro 0813 DeepSeek
36.0
 deepseek-ai/DeepSeek-V4-Pro-0813 56.1 $1.98
10
DeepSeek V4 Flash Vision Exp DeepSeek
34.8
 deepseek-ai/DeepSeek-V4-Flash-Vision-Exp Not enough data $1.32
11
DeepSeek V4 Flash 0731 DeepSeek
34.3
 deepseek-ai/DeepSeek-V4-Flash-0731 51.8 $0.396
12
Qwen3.8 27B Qwen
33.7
 Qwen/Qwen3.8-27B 74.2 $2.55
13
GLM 5.2 Z.ai
33.7
 zai-org/GLM-5.2 61.1 $4.40
14
DeepSeek V4 Pro 0423 DeepSeek
30.4
 deepseek-ai/DeepSeek-V4-Pro 38.7 $2.976
15
MiniMax M3 MiniMax
29.2
 MiniMaxAI/Minimax-M3 39.2 $1.20
16
GLM 5 Z.ai
27.9
 zai-org/GLM-5 41.7 $3.20
17
Kimi K2.6 Moonshot AI
27.0
 moonshotai/Kimi-K2.6 52.1 $4.00
18
Nemotron 3.5 Super VL NVIDIA
26.5
 nvidia/NVIDIA-Nemotron-3.5-Super-VL Not enough data $0.50
19
GLM 5.1 Z.ai
26.1
 zai-org/GLM-5.1 49.2 $4.40
20
MiMo-V2.5-Pro Xiaomi
26.0
 XiaomiMiMo/MiMo-V2.5-Pro 31.6 $0.9152

How this list is built

Generated from the dataset on every refresh. Nobody picks the order by hand.

Models on the AA Intelligence Index board that OpenRouter links to a public Hugging Face repository, by their AA Intelligence Index result. We do not check the license; read it on the repository page.

Other lists

Rankings beyond coding · Methodology