Free reasoning models

Models with a reasoning (chain-of-thought) mode: better than plain instruct models on multi-step problems, math, and analysis, at the cost of more tokens.

72 models13 providersup to 1M contextbest: GLM 5.3 FlashUpdated: November 2, 2026 at 05:25 PM UTC

Reasoning burns token quotas faster. Use Flash or non-reasoning modes for simple answers.

#	Model ↕	AA Index ↕	GPQA ↕	Context ↕	Size ↕	Free at ↕
1	GLM 5.3 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	41.8	91%	1M	Mid-size	OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen
2	GLM 5.3 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	44.8	92%	1M	Frontier	Together AI
3	DeepSeek V4.1 Flash DeepSeek ReasoningCodingTool useOpen weights	39.5	—	1M	Frontier	OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen
4	GLM 5.3 Flash Thinking Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	41.8	91%	1M	Mid-size	UnoRouter
5	Gemini 3.8 Flash Google VisionReasoningCodingTool use	40.9	95%	1M	Mid-size	Google AI Studio
6	Qwen 3.8 27B Alibaba Cloud · 27B ReasoningCodingTool useOpen weights	33.7	91%	262K	Mid-size	Groq, Cloudflare Workers AI, UnoRouter
7	DeepSeek V4 Flash DeepSeek ReasoningCodingTool useOpen weights	34.3	91%	1M	Frontier	OrcaRouter
8	Gemini 3.6 Flash Google VisionReasoningCodingTool use	34.0	93%	1M	Mid-size	UnoRouter
9	GLM 5.2 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	33.7	90%	1M	Frontier	Together AI
10	Inkling Small Thinking Machines Lab ReasoningOpen weights	27.8	90%	1M	Small	OpenRouter
11	Kimi K2.6 Moonshot AI ReasoningCodingTool useOpen weights	27.0	91%	256K	Frontier	NVIDIA Build
12	Nemotron 3 Ultra NVIDIA · 550B · 55B ReasoningCodingTool useOpen weights	22.9	87%	1M	Frontier	OpenRouter, NVIDIA Build, UnoRouter
13	Inkling Thinking Machines Lab ReasoningOpen weights	25.0	87%	1M	Small	OpenRouter
14	Gemini 3.5 Flash Lite Google VisionReasoningCoding	22.2	84%	1M	Small	UnoRouter
15	MiniMax M2.5 MiniMax ReasoningCodingTool useOpen weights	22.8	85%	205K	Frontier	UnoRouter
16	Qwen 3.5 397B Alibaba Cloud · 397B · 17B ReasoningCodingTool useOpen weights	21.4	86%	262K	Frontier	UnoRouter
17	Qwen 3.6 27B Alibaba Cloud · 27B ReasoningCodingTool useOpen weights	21.4	84%	262K	Mid-size	UnoRouter
18	GLM 4.7 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	22.2	86%	203K	Frontier	Together AI
19	Qwen 3.6 35B Alibaba Cloud · 35B · 3B ReasoningCodingTool useOpen weights	18.2	84%	262K	Mid-size	Together AI, UnoRouter
20	Step 3.7 Flash StepFun ReasoningTool useOpen weights	19.5	81%	262K	Frontier	Nous Portal
21	Qwen 3.5 35B Alibaba Cloud · 35B · 3B ReasoningCodingTool useOpen weights	19.3	85%	262K	Mid-size	Together AI
22	Nemotron 3.5 Lightning NVIDIA · 30B · 3B ReasoningTool useOpen weights	12.9	74%	1M	Mid-size	+1OpenRouter, NVIDIA Build, Vercel AI Gateway, UnoRouter, OpenCode Zen
23	Qwen 3.5 122B Alibaba Cloud · 122B · 10B ReasoningCodingTool useOpen weights	17.7	83%	262K	Frontier	Together AI
24	MiniMax M2 MiniMax · 230B · 10B ReasoningCodingTool useOpen weights	18.6	78%	197K	Frontier	Together AI
25	Gemini 3.1 Flash Lite Google VisionReasoningCoding	15.6	82%	1M	Small	UnoRouter
26	GLM 4.7 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	14.9	58%	131K	Mid-size	Cloudflare Workers AI, UnoRouter
27	Qwen 3.5 9B Alibaba Cloud · 9B ReasoningCodingOpen weights	13.7	81%	262K	Small	Together AI, UnoRouter
28	Qwen3 Coder Plus Alibaba Cloud ReasoningCodingTool useOpen weights	—	—	1M	Frontier	UnoRouter
29	Nemotron 3 Nano Omni NVIDIA · 30B · 3B VisionReasoningTool useOpen weights	10.3	47%	262K	Mid-size	+1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter
30	Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	NVIDIA Build, UnoRouter
31	Nemotron 3 120B NVIDIA · 120B · 12B ReasoningTool useOpen weights	—	—	256K	Frontier	Cloudflare Workers AI
32	gpt-oss-120b OpenAI · 117B · 5.1B ReasoningCodingTool useOpen weights	11.6	78%	131K	Frontier	Groq, Cloudflare Workers AI, UnoRouter
33	gpt-oss-20b OpenAI · 21B · 3.6B ReasoningTool useOpen weights	10.0	61%	131K	Mid-size	Groq, Cloudflare Workers AI, NVIDIA Build, UnoRouter
34	Qwen3 VL 235B Alibaba Cloud · 235B · 22B VisionReasoningTool useOpen weights	13.4	77%	262K	Frontier	Together AI
35	Qwen 3.5 4B Alibaba Cloud · 4B ReasoningCodingOpen weights	13.1	77%	262K	Small	UnoRouter
36	Nemotron 3.5 Super VL NVIDIA VisionReasoningTool useOpen weights	—	—	1M	Mid-size	OpenRouter, UnoRouter, OpenCode Zen
37	GLM 4.7 Fp4 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	203K	Frontier	Together AI
38	GLM 5 Fp4 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	203K	Frontier	Together AI
39	MiniMax M2.5 Fp4 MiniMax ReasoningCodingTool useOpen weights	—	—	8K	Frontier	Together AI
40	MiniMax M3.1 Flash MiniMax ReasoningCodingTool useOpen weights	—	—	—	Frontier	NVIDIA Build
41	Nemotron 3.5 Super VL 120B NVIDIA · 120B · 12B VisionReasoningTool useOpen weights	—	—	—	Frontier	NVIDIA Build
42	GLM 4 Z.ai (Zhipu AI) ReasoningTool useOpen weights	—	—	25K	Frontier	UnoRouter
43	Nvidia Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	Together AI
44	MiniMax M1 80K MiniMax ReasoningTool useOpen weights	11.7	70%	1M	Frontier	Together AI
45	Qwen3 235B Alibaba Cloud · 235B · 22B ReasoningCodingTool useOpen weights	12.7	79%	262K	Frontier	Together AI
46	Qwen3 30B Alibaba Cloud · 30B · 3B ReasoningTool useOpen weights	9.8	71%	262K	Mid-size	Together AI, Cloudflare Workers AI
47	Qwen3 Next 80B Alibaba Cloud · 80B · 3B ReasoningCodingTool useOpen weights	11.2	76%	262K	Frontier	Together AI
48	MiniMax M1 40K MiniMax ReasoningTool useOpen weights	10.0	68%	1M	Frontier	Together AI
49	QwQ 32B Alibaba Cloud · 32B ReasoningTool useOpen weights	9.5	59%	24K	Mid-size	Cloudflare Workers AI, UnoRouter
50	GLM 5.3 Flash Search Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	1M	Mid-size	UnoRouter
51	GLM 5.3 Flash Think Search Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	1M	Mid-size	UnoRouter
52	Qwen3 Coder 30B Alibaba Cloud · 30B · 3B ReasoningCodingTool useOpen weights	9.6	52%	262K	Frontier	Together AI
53	Qwen 3.5 27B Derestricted Alibaba Cloud · 27B ReasoningCodingTool useOpen weights	—	—	262K	Mid-size	UnoRouter
54	Nvidia Nemotron 3 Nano NVIDIA · 30B · 3B ReasoningTool useOpen weights	8.9	76%	262K	Mid-size	Together AI
55	DeepSeek R1 Distill Qwen 32B DeepSeek · 32B ReasoningTool useOpen weights	8.4	62%	80K	Mid-size	Cloudflare Workers AI, UnoRouter
56	Qwen3 4B Alibaba Cloud · 4B ReasoningOpen weights	8.8	67%	262K	Small	Together AI
57	Nemotron 3.5 Bolt E4b NVIDIA ReasoningTool useOpen weights	—	—	—	Mid-size	NVIDIA Build
58	GLM 4.5 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	131K	Mid-size	UnoRouter
59	GLM 4 6v Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	128K	Mid-size	UnoRouter
60	Qwen3 Alibaba Cloud ReasoningTool useOpen weights	—	—	25K	Mid-size	UnoRouter
61	Magistral Small Mistral AI ReasoningTool useOpen weights	8.6	66%	41K	Mid-size	Together AI
62	Qwen3 32B Alibaba Cloud · 32B ReasoningTool useOpen weights	8.6	67%	41K	Mid-size	Together AI
63	Qwen3 14B Alibaba Cloud · 14B ReasoningTool useOpen weights	8.2	60%	2K	Mid-size	Together AI
64	Qwen 3.5 2B Alibaba Cloud · 2B ReasoningCodingOpen weights	6.9	46%	262K	Small	Together AI
65	DeepSeek R1 Distill Llama 70B DeepSeek · 70B · New ReasoningTool useOpen weights	7.9	40%	131K	Frontier	UnoRouter
66	GLM 4 5v Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	7.6	68%	66K	Frontier	Together AI
67	Laguna XS 2.1 Poolside ReasoningCoding	—	—	262K	Small	NVIDIA Build, UnoRouter
68	Qwen3 8B Alibaba Cloud · 8B ReasoningOpen weights	7.3	59%	41K	Small	Together AI
69	Command A Reasoning 08 2025 Cohere · 111B · Legacy Reasoning	—	—	289K	Frontier	Cohere
70	Qwen 3.1 7B Alibaba Cloud · 1.7B ReasoningOpen weights	5.2	36%	41K	Small	Together AI
71	DeepSeek R1 Distill Qwen 7B DeepSeek · 7B ReasoningOpen weights	—	—	131K	Small	Together AI
72	Cosmos Reason2 8B NVIDIA · 8B VisionReasoning	—	—	—	Small	NVIDIA Build

Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.

FAQ

What is the best free model for reasoning?

GLM 5.3 Flash currently leads — free at OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen. Next come GLM 5.3, DeepSeek V4.1 Flash, GLM 5.3 Flash Thinking.

FAQ

See also