Best Math LLMs — Page 12

qwen3-4b-instruct-2507-retool-grpo

VibeThinker-3B

Sombrero-R1-14B-Elite13

Aristaeus

Fast-Math-R1-14B

qwen2.5-0.5b-gsm8k

phi-4-abliterated

Ouro-1.4B-Thinking-depth-SFT

Qwen2.5-3B-GRPO-Staleness-8

DeepMath-Zero-7B

deepseek-r1-distill-qwen-14b-fast-math-r1-sft-10ep

qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont

VPR-Qwen3-4B-Base-Math-Mixed

DeepMath-Zero-Math-7B

qwen3-4b-grpo-tr-matematik-merged

qwen2_5_math_1_5b_Instruct-NSFW-U-V3.1

GanitLLM-4B_CGRPO

qwen3-0.6b-math-l45-qlora-merged-fp16

Qwen3-4B-Thinking-2507-GLM-4.7-Distilled

Phi-4-reasoning-plus

Qwen3-4B-openthoughts3-math-400k-sft

M-Thinker-7B-Iter2

Qwen3-8B-openthoughts3-math-400k-sft

Qwen3-4B-Inst-Math-Reasoning-SFT

llama2_7b_chat_seal_5e-5

Qwen3-1.7B-OPD-fwdKL-from-Qwen3-8B-GRPO

Phi-4-reasoning

ssft-32B-N6

deped-math-qwen2.5-7b-deped-math-merged

Jan-v3.5-4B-mlx-fp16

phi-4

Qwen3-8B-SPoT

Miner-8B

CRISP-Qwen3-14B-v1

Kepler-Reasoning-7B

Llama-3.2-3B-ThinkSFT

VibeThinker-3B-MLX

CRISP-Qwen3-14B-v2

dsr1-qwen7b-sgd-polaris-step100-best-val

dsr1-qwen7b-sgd-polaris-step412-final

Qwen3-1.7B-OPD-step120

Phi-4-mini-reasoning