Our new X account is live! Follow @wizwand_team for updates

Reasoning on MMLU-Pro

90.1Accuracy

Gemini-3.0 Pro

Updated 3d ago

Evaluation Results

Method	Links
Gemini-3.0 Pro 2026.01		90.1
Claude Sonnet 4.5 2026.01		88.2
GPT-5 High 2026.01		87.5
DeepSeek-V3.2 Thinking 2026.01		85
MiMo-V2-Flash 2026.01		84.9
Kimi-K2 Thinking 2026.01		84.6
FP16 2025.11		78.1
QTIP 2025.11		77.9
ParoQuant 2025.11		77.5
AWQ 2025.11		77.2
E-QAT 2025.11		76.5
FP16 2025.11		74.6
ParoQuant 2025.11		74.1
QTIP 2025.11		74
AWQ 2025.11		73.5
E-QAT 2025.11		73.4
T3S 2026.01		73.09
T3S 2026.01		72.88
T3S 2026.01		72.65
T3S 2026.01		72.65
SFT 2026.01		71.73
SFT 2026.01		71.48
Base 2026.01		71.42
SFT 2026.01		71.21
FP16 2025.11		71
ParoQuant 2025.11		70.1
SFT 2026.01		69.92
QTIP 2025.11		69.7
AWQ 2025.11		68.2
E-QAT 2025.11		67.7
FP16 2025.11		58.8
Qwen2.5-7B-Instruct 2026.02		57.4
QTIP 2025.11		57.4
ParoQuant 2025.11		57.1
AWQ 2025.11		56
E-QAT 2025.11		55.6
LGT 2025.11		51.07
LGT 2025.11		49.82
LPT 2025.11		48.74
Qwen2.5-Omni-7B 2025.11		47
Virgo 2025.11		39.21
KEEL 2026.01		35.6
s1.1-7B 2026.02		28.7
Pre-LN 2026.01		26.6
DGR SFT 2026.02		20.1
DGR SFT 2026.02		18.9
Vanilla SFT 2026.02		11.5
Vanilla SFT 2026.02		11
DGR SFT 2026.02		7.6
Vanilla SFT 2026.02		4.3