Share your thoughts, 1 month free Claude Pro on usSee more

General Knowledge on MMLU-Pro (Accuracy)

86.7Accuracy

Qwen3.5-122B-A10B

Updated 18d ago

Evaluation Results

Method	Links
Qwen3.5-122B-A10B 2026.04		86.7
Qwen-3.5 27B 2026.04		86.1
Super 2026.07		83.8
Nemotron 3 Super 2026.04		83.73
Super 2026.07		83.5
Puzzle-75B-A9B 2026.07		82.4
Puzzle-75B-A9B 2026.07		82.2
Qwen3.5-35B-A3B 2026.04		81.6
JoyAI-LLM Flash 2026.04		81.6
GPT-OSS-120B 2026.04		81
Apriel-1.6 2026.04		78.8
Qwen3-30B-A3B 2026.04		78.7
Nemotron-3-Nano 30B 2026.04		78.3
Nemotron-Nano 12B v2 2026.04		77.2
all-attention 2026.04		76.8
Qwen3-Next-80B-A3B 2026.04		76.7
Reg\|Lklhd–18 2026.04		76.3
Idealized\|All–18 2026.04		76.3
Reg\|Lklhd–26 2026.04		76.2
GLM-4.7-Flash-T 2026.04		75.8
S1: Distil. Idealized\|All–6 2026.04		74.5
Idealized\|Lklhd–6 2026.04		73.6
Idealized\|All–6 2026.04		73.3
JoyAI-LLM Flash-Base 2026.04		73.1
Qwen 2025.09		73
Falcon-H1R 7B 2026.04		72.5
Reg\|Lklhd–13 2026.04		69.3
Reg\|Lklhd–10 2026.04		68.2
Apriel-H1 15B 2026.04		67.5
Qwen 2025.09		66
Qwen 2025.09		66
OLMo-Hybrid-Think 7B 2026.04		65.7
Qwen3-30B-A3B-Base 2026.04		61.7
Qwen3.5-35B-A3B-Base 2026.04		60.7
SDAR-8B 2026.06		56.9
OPDLM-8B 2026.06		53.7
Qwen3 2025.10		51.4
SDAR-4B 2026.06		50.9
Ouro 2025.10		48.62
OPDLM-4B 2026.06		46.3
LLaMA 2025.09		46
Dream-7B 2026.06		43.3
Fast-dLLM-v2-7B 2026.06		41.5
MSA-CPT 2026.06		39.1
MSA-PT 2026.06		38.8
Full 2026.06		38.5
Qwen2.5 2025.10		37.87
Qwen3 2025.10		37.27
LLaMA 2025.09		37
LLaDA-8B 2026.06		37
LLaMA 2025.09		36
Gemma3 2025.10		34.61
Llama3.2 2025.10		33.34
Qwen2.5 2025.10		29.11
EMM 2026.06		28.1
MERGEvolve 2026.06		27.17
Pack of LLMs 2026.06		27.07
LoraHub 2026.06		27.03
Pack of LLMs 2026.06		26.97
Model Swarms 2026.06		26.92
MERGEvolve 2026.06		26.63
EMM 2026.06		26.54
Model Swarms 2026.06		26.47
LoraHub 2026.06		26.15
Expert Fusion 2026.06		25.3
Llama3.2 2025.10		11.8
Gemma3 2025.10		11.31