Best Math LLMs — Page 11

Megatron-Opus-14B-Exp

gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4_merged

Qwen-B3PO-7B

Qwen-C3PO-7B

qwen2.5-1.5b-grpo-gsm8k

dagger-12B_SFT_GRPO

IncorrectTraceSFT-Qwen2.5-7B-MATH-random-mask-80

IncorrectTraceSFT-Qwen2.5-7B-AIME2024-correct

SOD-0.6B

Qwen3-4B-AMQ3-Math-SFT

Qwen2.5-7B-ViMetaMathQA-Mini

Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29

Qwen3.5-9B-OPSA

qwen3-1.7b-gsm8k-sft

CRISP-Qwen3-8B-v1

qwen3-0.6b-grpo-math-reasoning

verl-math-transfer-7bi-to-7bi-v2

Ouro-1.4B-Thinking-depth-GRPO

phi-4

IncorrectTraceSFT-Qwen2.5-7B-AIME-SplitB-incorrect

MathReasoner-Mini-1.5b

math_model

Epimetheus-14B-Axo

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

dagger-12B_GRPO

DeepMath-103K-Level6-Qwen3-4B-Base-GRPO

math-think-q8b-20260908

Qwen2.5-3B-Instruct-Sheldon-SFT-v2-merged

IncorrectTraceSFT-Qwen2.5-7B-AIME2025-incorrect

gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-16_merged

phi-4

dagger-4B_SFT_GRPO

Deepthink-1.5B-Open-PRM

MNLP_SFT_DPO

qwen3-8b-jee-sft

ThinkTwice-Qwen3-4B-Instruct

dqnMath-v1

Qwen3.5-2b-ReMix

Qwen3-8B-PlumEsper

verl-math-transfer-7bi-to-3bi-fix03

DeepMath-Omn-1.5B

Qwen3-8B-ODA-Math-460k