Best Reasoning LLMs — Page 26

Qwen3-0.6B-Code

Qwen3-8B-SW-Pivot-EN

VibeThinker-3B-mlx-fp16

Qwen3-0.6B-GRPO

Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated

Rogue-28B-MIX

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

general_knowledge_model

A1

OpenMythos-9B-1M-heretic

matutake

Qwen3-1.7B-gpt-oss-distill

gemma-4-12B-coder-fable5-composer2.5-v1-heretic

Dhanishtha-2.0-preview-mlx

MNLP_SFT_DPO

Co-rewarding-I-Qwen3-8B-Base-DAPO14k

Phi-4-reasoning-heretic

Ouro-2.6B-Thinking

gemma-3-1b-it-amr_thinking

Kepler-Reasoning-7B

Qwen3-4B-GRPO

Qwen3-1.7B-GRPO

Qwen3-0.6B-MBT-R

vibethinker-3b-mlx

ssft-32B-N6

VALOR-8B

Qwen3-8B-SPoT

phi3-mini-reasoning-beast

qwen3-vl-8b-thinking-physics-r2-sft-v1

Quintus

Rehber-Science

gemma-4-e4b-opus-reasoning-v2

CRISP-Qwen3-14B-v1

EvoNet-8b-Reasoning

conflict-env-final

Noir

Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-600steps

VLM-CapCurriculum-Qwen3-VL-8B-Staged

Qwen3-8B-DE-Pivot-EN

Mythos-weights

jojangju-KR-31B

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