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

Mathematical Reasoning on OMEGA

53.4Score

Olmo 3.1 Think 32B

Updated 2d ago

Evaluation Results

Method	Links
Olmo 3.1 Think 32B 2025.12		53.4
Qwen 3 VL 32B Think 2025.12		50.8
Olmo 3 Think (Final 3.0) 2025.12		50.6
Qwen 3 32B 2025.12		47.7
K2-V2 70B Instruct 2025.12		46.1
Olmo 3 Think (DPO) 2025.12		45.2
Olmo 3 7B Think 2025.12		45
Qwen 3 8B 2025.12		43.4
OR Nemotron 7B 2025.12		43.2
Olmo 3 Think (SFT) 2025.12		43.1
Nemotron Nano 9B v2 2025.12		42.4
Olmo 3 7B Think 2025.12		40.5
DS-R1 32B 2025.12		38.9
OpenThinker3 7B 2025.12		38.4
Qwen 3 VL 8B Think 2025.12		38.1
Olmo 3 7B Think 2025.12		37.8
Qwen 3 VL 8B Inst 2025.12		32.3
Olmo 3 7B Instruct 2025.12		28.9
DS-R1 Qwen 7B 2025.12		28.5
Olmo 3 7B Instruct 2025.12		22.8
Qwen 3 8B 2025.12		20.5
Gemma 3 12B 2026.02		15.19
DictaLM 3.0 12B-Inst 2026.02		15.19
Olmo 3 7B Instruct 2025.12		14.4
Qwen 2.5 7B 2025.12		13.7
Granite 3.3 8B Inst 2025.12		10.7
OLMo 2 7B Inst 2025.12		5.2
Apertus 8B Inst 2025.12		5