Performance ranking (third-party evaluations)

Performance ranking by LMArena

Scores computed from people voting between two models' answers (Bradley-Terry, with style control). The range is the 95% interval; differences between models whose ranges overlap are not clear.

Top 45 of 45 models listed on this site

Values as of Nov 9, 2026

Rank Model Score (95% interval) Memory at 8K
1

Kimi-K2.6
moonshotai 1,026.4B Kimi K2.6

Score (95% interval) 1,461 1,456–1,465

39,573 votes

UD-Q2_K_XL 342 GB
2

Hy3
tencent 295B hy3

Score (95% interval) 1,454 1,449–1,460

15,068 votes

Q4_K_M 186 GB
3

Qwen3.5-397B-A17B
Qwen 396.3B qwen3.5-397b-a17b

Score (95% interval) 1,441 1,438–1,445

97,678 votes

Q4_K_M 246 GB
4

DeepSeek-V4-Flash
deepseek-ai 284.3B deepseek-v4-flash

Score (95% interval) 1,436 1,432–1,440

51,368 votes

UD-IQ1_S 83.4 GB
5

Qwen3.8-27B
Qwen 27.3B qwen3.8-27b

Score (95% interval) 1,433 1,429–1,438

32,659 votes

UD-Q4_K_M 18.2 GB
6

DeepSeek-R1-0528
deepseek-ai 671B DeepSeek-R1 (0528)

Score (95% interval) 1,421 1,416–1,427

18,153 votes

Q4_K_M 411 GB
7

Qwen3.5-122B-A10B
Qwen 122.1B qwen3.5-122b-a10b

Score (95% interval) 1,416 1,412–1,421

29,496 votes

Q4_K_M 77.9 GB
8

Qwen3.5-27B
Qwen 26.9B qwen3.5-27b

Score (95% interval) 1,409 1,404–1,413

28,424 votes

Q4_K_M 18.5 GB
9

Qwen3-Next-80B-A3B-Instruct
Qwen 79.7B qwen3-next-80b-a3b-instruct

Score (95% interval) 1,399 1,394–1,403

22,692 votes

Q4_K_M 49.6 GB
10

DeepSeek-R1
deepseek-ai 671B deepseek-r1

Score (95% interval) 1,398 1,393–1,403

18,524 votes

Q4_K_M 446 GB
11

DeepSeek-V3-0324
deepseek-ai 671B DeepSeek-V3 (0324)

Score (95% interval) 1,395 1,391–1,399

44,918 votes

IQ1_S 175 GB
12

Qwen3-VL-235B-A22B-Thinking
Qwen 235.1B qwen3-vl-235b-a22b-thinking

Score (95% interval) 1,395 1,388–1,402

7,835 votes

Q4_K_M 145 GB
13

Qwen3.5-35B-A3B
Qwen 34.7B qwen3.5-35b-a3b

Score (95% interval) 1,394 1,390–1,398

30,206 votes

Q4_K_M 23.3 GB
14

Qwen3-30B-A3B-Instruct-2507
Qwen 30.5B Qwen3-30B-A3B-Instruct (2507)

Score (95% interval) 1,382 1,377–1,387

23,287 votes

Q4_K_M 20.2 GB
15

GLM-4.5-Air
zai-org 110.5B glm-4.5-air

Score (95% interval) 1,373 1,369–1,377

30,591 votes

Q4_K_M 75.6 GB
16

Qwen3-Next-80B-A3B-Thinking
Qwen 79.7B qwen3-next-80b-a3b-thinking

Score (95% interval) 1,369 1,364–1,375

13,450 votes

Q4_K_M 49.6 GB
17

gemma-3-27b-it
google 27B Gemma 3 27B IT

Score (95% interval) 1,365 1,362–1,369

46,613 votes

Q4_K_M 18.9 GB
18

GLM-4.7-Flash
zai-org 29.9B glm-4.7-flash

Score (95% interval) 1,364 1,359–1,370

11,937 votes

Q4_K_M 19.6 GB
19

gpt-oss-120b
openai 116.8B gpt-oss-120b

Score (95% interval) 1,352 1,347–1,356

30,133 votes

MXFP4 64.7 GB
20

Qwen3-32B
Qwen 32.8B qwen3-32b

Score (95% interval) 1,347 1,337–1,356

3,926 votes

Q4_K_M 22.8 GB
21

gemma-3-12b-it
google 11.8B Gemma 3 12B IT

Score (95% interval) 1,342 1,332–1,351

3,829 votes

Q4_K_M 9.41 GB
22

granite-4.2-30b
ibm-granite 29.3B Granite 4.2 30B

Score (95% interval) 1,340 1,329–1,350

3,314 votes

Q4_K_M 20.6 GB
23

QwQ-32B
Qwen 32.8B qwq-32b

Score (95% interval) 1,336 1,331–1,340

25,166 votes

Q4_K_M 22.8 GB
24

Qwen3-30B-A3B
Qwen 30.5B qwen3-30b-a3b

Score (95% interval) 1,326 1,322–1,331

26,137 votes

Q4_K_M 20.2 GB
25

Llama-4-Scout-17B-16E-Instruct
meta-llama 107.8B Llama 4 Scout 17B 16E Instruct

Score (95% interval) 1,322 1,317–1,326

29,777 votes

Q4_K_M 67.9 GB
26

Llama-3.3-70B-Instruct
meta-llama 70.6B Llama 3.3 70B Instruct

Score (95% interval) 1,318 1,315–1,322

54,482 votes

Q4_K_M 46.0 GB
27

gpt-oss-20b
openai 20.9B gpt-oss-20b

Score (95% interval) 1,318 1,311–1,324

10,400 votes

Q4_K_M 12.8 GB
28

gemma-3n-E4B-it
google 6.9B Gemma 3n E4B IT

Score (95% interval) 1,317 1,312–1,323

22,106 votes

Q4_K_M 5.71 GB
29

gemma-3-4b-it
google 3.9B Gemma 3 4B IT

Score (95% interval) 1,303 1,294–1,313

4,171 votes

Q4_K_M 3.91 GB
30

Qwen2.5-72B-Instruct
Qwen 72.7B qwen2.5-72b-instruct

Score (95% interval) 1,303 1,299–1,307

39,406 votes

Q4_K_M 50.9 GB
31

gemma-2-27b-it
google 27.2B Gemma 2 27B IT

Score (95% interval) 1,290 1,286–1,293

75,754 votes

Q4_K_M 20.1 GB
32

granite-4.2-8b
ibm-granite 8.8B Granite 4.2 8B

Score (95% interval) 1,290 1,278–1,301

3,196 votes

Q4_K_M 7.43 GB
33

granite-4.2-3b
ibm-granite 3.7B Granite 4.2 3B

Score (95% interval) 1,289 1,277–1,301

3,185 votes

Q4_K_M 3.66 GB
34

Mistral-Small-24B-Instruct-2501
mistralai 23.6B Mistral Small 24B Instruct (2501)

Score (95% interval) 1,274 1,268–1,280

14,681 votes

Q4_K_M 16.5 GB
35

Qwen2.5-Coder-32B-Instruct
Qwen 32.8B qwen2.5-coder-32b-instruct

Score (95% interval) 1,271 1,263–1,279

5,432 votes

Q4_K_M 22.8 GB
36

gemma-2-9b-it
google 9.2B Gemma 2 9B IT

Score (95% interval) 1,267 1,263–1,271

54,611 votes

Q4_K_M 9.02 GB
37

phi-4
microsoft 14.7B phi-4

Score (95% interval) 1,256 1,252–1,261

24,126 votes

Q4_K_M 11.5 GB
38

Mixtral-8x22B-Instruct-v0.1
mistralai 140.6B Mixtral 8x22B Instruct v0.1

Score (95% interval) 1,230 1,225–1,234

51,416 votes

IQ1_S 32.1 GB
39

gemma-2-2b-it
google 2.6B Gemma 2 2B IT

Score (95% interval) 1,200 1,196–1,204

46,616 votes

Q4_K_M 3.45 GB
40

Llama-3.2-3B-Instruct
meta-llama 3.2B Llama 3.2 3B Instruct

Score (95% interval) 1,167 1,159–1,175

7,936 votes

Q4_K_M 3.76 GB
41

Mistral-7B-Instruct-v0.2
mistralai 7.2B Mistral 7B Instruct v0.2

Score (95% interval) 1,149 1,143–1,156

19,402 votes

Q4_K_M 6.04 GB
42

Phi-3-mini-4k-instruct
microsoft 3.8B Phi-3 Mini 4K Instruct

Score (95% interval) 1,128 1,122–1,135

20,118 votes

-
43

Llama-3.2-1B-Instruct
meta-llama 1.2B Llama 3.2 1B Instruct

Score (95% interval) 1,111 1,103–1,119

8,045 votes

Q4_K_M 1.88 GB
44

Llama-2-7B-Chat
TheBloke 6.7B Llama 2 7B Chat

Score (95% interval) 1,108 1,101–1,115

14,148 votes

-
45

gemma-2b-it
lmstudio-ai 2.5B Gemma 2B IT

Score (95% interval) 1,094 1,082–1,105

4,780 votes

Q4_K_M 2.72 GB

Estimated Memory at 8K: Estimated with a formula. Actual usage depends on your setup and settings.

About this ranking

Values for open-weight models come from the latest version of LMArena's Hugging Face dataset (text, style control, overall). Updated weekly.
Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.
Values are attached only when the model name in the source matches a model listed on this site (its original Hugging Face repository). Fine-tunes and modified versions do not get them.
Each source is a separate ranking. We do not mix values from different sources or assign our own scores.
Small and new models are often not evaluated by the source, so they do not appear here.

Values are from LMArena data (CC BY 4.0), shown unchanged (sorting and filtering by this site).