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

Mathematical Reasoning on MATH (Score)

96.7Score

Qwen 3 VL 32B Think

Updated 4d ago

Evaluation Results

Method	Links
Qwen 3 VL 32B Think 2025.12		96.7
Olmo 3.1 Think 32B 2025.12		96.2
Olmo 3 Think (Final 3.0) 2025.12		96.1
Olmo 3 Think (DPO) 2025.12		95.9
Olmo 3 Think (SFT) 2025.12		95.6
Qwen 3 32B 2025.12		95.4
Qwen 3 VL 8B Think 2025.12		95.2
Olmo 3 7B Think 2025.12		95.1
Qwen 3 8B 2025.12		95.1
OR Nemotron 7B 2025.12		94.6
K2-V2 70B Instruct 2025.12		94.5
OpenThinker3 7B 2025.12		94.5
Olmo 3 7B Think 2025.12		94.4
Nemotron Nano 9B v2 2025.12		94.4
DS-R1 32B 2025.12		92.6
Olmo 3 7B Think 2025.12		92.4
DS-R1 Qwen 7B 2025.12		87.9
GHS-TDA 2026.02		77.19
AoT 2026.02		76.91
GoT 2026.02		76.36
ToT 2026.02		72.86
CoT 2026.02		72.04
GHS-TDA 2026.02		68.4
AoT 2026.02		66.2
GoT 2026.02		65.7
ToT 2026.02		65
CoT 2026.02		60.8
LLM-in-Sandbox-RL 2026.01		53.3
LLM-in-Sandbox-RL 2026.01		51
LLM-RL 2026.01		48.5
Base LLM 2026.01		46
Qwen2-7B 2024.07		44.2
LLM-in-Sandbox-RL 2026.01		42.7
Base LLM 2026.01		41.5
LLM-RL 2026.01		40.9
LLM-RL 2026.01		33.1
Base LLM 2026.01		32.5
LLM-in-Sandbox-RL 2026.01		29.8
LLM-RL 2026.01		28.1
Base LLM 2026.01		26
Gemma-7B 2024.07		24.3
Llama-3-8B 2024.07		20.5
Qwen1.5-7B 2024.07		20.3
Mistral-7B 2024.07		13.1
Phi-4 2026.01		0.801
Llama-3.3-70B-Instruct 2026.01		0.739
Llama-3.1-8B-Instruct 2026.01		0.479
Foundation-Sec-8B-Instruct 2026.01		0.436
Foundation-Sec-8B-Reasoning 2026.01		0.433
Llama-Primus-Merged 2026.01		0.398