Best Math LLMs — Page 8

Qwen3-8B-Base-OT3Math-SFT-step500

ThinkLess-2B

gifted_maths_unsloth_remerged_full_gemma_4

qwen3-8b-sft-261001-bigmath-sol-fsdp-0-epoch-4

sherlock-qwen2.5-3b-grpo-v1

qwen-Manimator-1-merged

qwen-3.5-27b-absorb

Qwen2.5-1.5B-Numina35k-Countdown10k-SFT-10k

Qwen2.5-1.5B-Numina30k-Countdown10k-SFT-10k

AOS-qwen3-8b-narrated-sft-merged

Bharat-Tiny-LLM-v3.4

qwen25-0.5b-finemath-4plus-openmath-sft

Math_DeepSeek-R1-Distill-Qwen-1.5B_JustRL-DeepSeek-1.5B

Math_Qwen3-1.7B_Qwen3-4B-Non-Thinking-RL-Math-Step500

Qwen3-8B-Base-OpenThoughts3Math-SFT-step750-lr5e-6

Qwen3-8B-Base-OpenThoughts3Math-SFT-step250-lr5e-6

Morphy-Math-1.5B

Phi-4-reasoning-heretic

qwen3-4b-recursive-sft-v3.2

Qwen3-4B-TIS-repro-final

ThinkLess-2B-SFT

Qwen3-4B-SC-TIS-repro-final

Q3.6-27B-GLM-5.1-DA

qwen3-4b-questa-nonmcq-estep-pos20-neg20-truncneg20-step50

Qwen3.5-4B-MultiDistill-3xMerge

Qwen3-1.7B-OPSA

Mythos-Nano

Qwen2.5-3B-OpenR1-SFT

Qwen3.5-4B-KIMI-Distill

OpenMath2-Llama3.1-70B

Qwen3.5-4B-RL-MATH

Qwen2.5-3B-GRPO-Staleness-4

qwen3.5-4b-reduction-coldstart

neural-chat-7b-v3-2

Mythos-nano

Qwen3-4B-Base-GRPO-MATH-ck300

Qwen2.5-Math-7B-GRPO-Staleness-4

Llama-3.1-8B-math-reasoning

Qwen2.5Math-IVON-SFT-7B

Qwen3-4B-Math-RL-Specialist

Phi-4-reasoning-plus

Sparky-4B-V1