Enter opens the highlighted result. Esc closes.

Best open-weight LLM overall

MiMo-V2.6-Pro leads
68.4
models ranked
57
downloads of #1, 30 days
103.9K
lead over #2
+0.5

Overall index · read October 21

  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 21, 2026, Xiaomi MiMo-V2.6-Pro leads 57 models that qualify, with 68.4 on the overall index, ahead of Z.ai GLM 5.3 (67.9) and DeepSeek V4.1 Flash 1017 (67.6).

Top 20 of 57, higher is better

Embed this data
Best open-weight LLM overall
Rank Model Overall index Evidence Coding index Output $/Mtok
1
MiMo-V2.6-Pro Xiaomi
68.4
 65.4 $0.87
2
GLM 5.3 Z.ai
67.9
 70.6 $4.40
3
DeepSeek V4.1 Flash 1017 DeepSeek
67.6
 70.3 $0.60
4
Kimi K3 Moonshot AI
66.5
 62.3 $15.00
5
GLM 5.3 Flash Z.ai
66.0
 57.7 $0.50
6
GLM 5.2 Z.ai
62.5
 61.1 $4.40
7
DeepSeek V4.1 Flash DeepSeek
62.4
 62.5 $0.78
8
DeepSeek V4 Pro 0813 DeepSeek
60.8
 56.1 $1.98
9
MiMo-V2.6-Flash Xiaomi
60.8
 54.7 $0.28
10
Step 5 Preview StepFun
60.5
 61.1 $2.70
11
Kimi K2.6 Moonshot AI
60.5
 52.1 $4.00
12
Qwen3.8 27B Qwen
59.6
 74.2 $2.55
13
GLM 5.1 Z.ai
57.5
 49.2 $4.40
14
Qwen3.5 397B A17B Qwen
57.1
 Not enough data $2.34
15
GLM 4.7 Z.ai
56.9
 55.1 $2.20
16
Kimi K2.7 Code Moonshot AI
56.7
 53.4 $4.00
17
DeepSeek V4 Flash Vision Exp DeepSeek
56.4
 Not enough data $1.32
18
DeepSeek V4 Flash 0731 DeepSeek
55.2
 51.8 $0.28
19
Gemma 4 26B A4B Google
54.7
 Not enough data $0.60
20
GLM 5 Z.ai
54.3
 41.7 $3.20

How this list is built

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

Models OpenRouter links to a public Hugging Face repository (we do not check the license), ordered by the LLMBenchmark Index, highest first. The index is our own 0 to 100 composite of our five skill indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.

Other lists

Rankings beyond coding · Methodology