Best Math LLMs — Page 6

Qwen3-4B-Base-GRPO

Q-SS-0.5B-Reasoning-Math

nexus-1.5b

MAXWELL

Logics-Qwen3-Math-4B

MetaMath-Cybertron

Merged-AGI-7B

Hercules-2.0-Mistral-7B

Hercules-2.5-Mistral-7B

Pearl-7B-0210-ties

Pearl-7B-0211-ties

Einstein-v5-v0.2-7B

OpenCerebrum-1.0-7b-SFT

OpenCerebrum-1.0-7b-DPO

Maxine-7B-0401-stock

Einstein-v6-7B

OpenCerebrum-2.0-7B

CosmicNoodle-7B

Einstein-v4-Qwen-1.5-32B

dart-math-mistral-7b-prop2diff

MR_midtrain_9B_v3

Qwen3-1.7B-Coder-Distilled-SFT

Pluto-Genesis-0.6B

LFM2.5-1.2B-Distilled-SFT

GRaPE-2-Mini

DualMind-TKD-Agentic-1.7B

qwen05b-gsm8k-sft-instruct

qwen2.5-7b-base-retool-slime-sft

qwen3-1p7b-sgd-polaris-step300-best-val

math-llm-sit-7b

qwen25-7b-ot-ideal-q3_32b-clean

Llama-3.2-3B-ThinkSFT

Argonne-Qwen1.5-0.5B-think

Myth-4B

qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont

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

Kepler-Reasoning-7B

aime-gen-qwen3-4b-v3

CRISP-DeepSeek-R1-Distill-Llama-8B-v1

MathReasoner-Mini-1.5b

CRISP-Qwen3-14B-v1

CRISP-Qwen3-8B-v2