MMLU-ProX

MMLU-ProX - Benchmark Leaderboard & Model Performance | AI Stats

Models Using This Benchmark

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Qwen	Qwen 3.6 Plus	01 Apr 2026	84.70	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 397B A17B	16 Feb 2026	84.70	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 122B A10B	24 Feb 2026	82.20	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 27B	24 Feb 2026	82.20	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 Flash	23 Feb 2026	82.20	LLM Stats (ZeroEval) \| inferred family alias from qwen3.5-27b (score=0.4147; benches=81)	Yes	Source
Qwen	Qwen 3 235B A22B Thinking 2507	-	81.00	LLM Stats (ZeroEval) \| MMLU-ProX	Yes	Source
Qwen	Qwen 3.5 35B A3B	24 Feb 2026	81.00	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 235B A22B Thinking	-	80.60	LLM Stats (ZeroEval)	Yes	Source
Nvidia	Nemotron 3 Super	11 Mar 2026	79.36	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 Next 80B A3B Thinking	-	78.70	LLM Stats (ZeroEval) \| MMLU-ProX	Yes	Source
Qwen	Qwen 3 VL 235B A22B Instruct	-	77.80	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 32B Thinking	-	77.20	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 Next 80B A3B Instruct	-	76.70	LLM Stats (ZeroEval) \| MMLU-ProX	Yes	Source
Qwen	Qwen 3.5 9B	02 Mar 2026	76.30	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 30B A3B Thinking	-	76.10	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 32B Instruct	-	73.40	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 4B	02 Mar 2026	71.50	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 30B A3B Instruct	-	70.90	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 8B	-	70.70	LLM Stats (ZeroEval) \| inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50)	Yes	Source
Qwen	Qwen 3 Embedding 8B	-	70.70	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	Source
Qwen	Qwen 3 Guard Gen 8B	-	70.70	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-8b-thinking (score=0.3400; benches=50)	Yes	Source
Qwen	Qwen 3 Guard Stream 8B	-	70.70	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50)	Yes	Source
Qwen	Qwen 3 Reranker 8B	-	70.70	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-8b-thinking (score=0.3850; benches=50)	Yes	Source
Qwen	Qwen 3 VL 8B Thinking	-	70.70	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL Embedding 8B	-	70.70	LLM Stats (ZeroEval) \| inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50)	Yes	Source
Qwen	Qwen 3 VL Reranker 8B	-	70.70	LLM Stats (ZeroEval) \| inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50)	Yes	Source
Qwen	Qwen 3 VL 8B Instruct	-	65.40	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 4B Instruct 2507	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	Source
Qwen	Qwen 3 4B SafeRL	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	Source
Qwen	Qwen 3 4B Thinking 2507	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48)	Yes	Source
Qwen	Qwen 3 Embedding 4B	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	Source
Qwen	Qwen 3 Guard Gen 4B	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48)	Yes	Source
Qwen	Qwen 3 Guard Stream 4B	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48)	Yes	Source
Qwen	Qwen 3 Reranker 4B	-	65.00	LLM Stats (ZeroEval) \| inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48)	Yes	Source
Qwen	Qwen 3 VL 4B Thinking	-	65.00	LLM Stats (ZeroEval)	Yes	Source
Nvidia	Nemotron Nano 3 30B A3B	15 Dec 2025	59.50	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3 VL 4B Instruct	-	59.40	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 2B	02 Mar 2026	52.30	LLM Stats (ZeroEval)	Yes	Source
Qwen	Qwen 3.5 0.8B	02 Mar 2026	34.60	LLM Stats (ZeroEval)	Yes	Source

Recorded Results

Average Score

Score Range

Leading Model

Models Using This Benchmark