geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk

COMPARE.

AI
Filters

Filter AI models

Brand
Benchmark coverage
Clear all filters
Type
6,278 results
openai

GPT-5.2 Codex

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
272,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
openai

GPT-5.2 Pro

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
272,000 tokens*
ECI 156.5*General capability index
zhipuai

AutoGLM Phone 9B Multilingual

Models
Context window
65,536 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Devstral Small 2

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Devstral 2

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
zhipuai

GLM-4.6V

Models
Context window
128,000 tokens
Maximum output
32,768 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
zhipuai

GLM-4.6V-Flash

Models
Context window
128,000 tokens
Maximum output
32,768 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
relace

Relace Search

Models
Context window
256,000 tokens
Maximum output
128,000 tokens
Open weights
No
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
essentialai

Rnj-1 Instruct

Models
Context window
32,768 tokens
Maximum output
32,768 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Mistral Large 3

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Maximum input
262,144 tokens*
Reported score · version unreported · intelligence15.90*Platform unreported
Arena 1428.3Human preference · 88,325 votes
amazon

Nova 2 Lite

Models
Context window
1,000,000 tokens
Maximum output
65,536 tokens
Open weights
No
Reasoning
Yes
Arena 1361.8Human preference · 12,413 votes
mistral

Devstral 2 (latest)

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 14B

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 14B

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 3B

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 8B

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 14B 2512

Models
Context window
262,144 tokens
Maximum output
209,715 tokens
Open weights
Yes
Maximum input
262,144 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 3B 2512

Models
Context window
131,072 tokens
Maximum output
104,857 tokens
Open weights
Yes
Maximum input
131,072 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Ministral 3 8B 2512

Models
Context window
262,144 tokens
Maximum output
209,715 tokens
Open weights
Yes
Maximum input
262,144 tokens*
Radar · unrated0/4 core tests · not enough evidence
deepseek

DeepSeek V3.2

Models
Context window
128,000 tokens
Maximum output
64,000 tokens
Open weights
Yes
Maximum input
Reported value 1: 163,840 tokens*
Reported value 2: 164,000 tokens*
ECI 146.1*General capability index
deepseek

DeepSeek Chat

Models
Context window
1,000,000 tokens
Maximum output
384,000 tokens
Open weights
Yes
Maximum input
131,072 tokens*
Radar · unrated1/4 core tests · not enough evidencedeepseek-chat
deepseek

DeepSeek Reasoner

Models
Context window
1,000,000 tokens
Maximum output
384,000 tokens
Open weights
Yes
Maximum input
131,072 tokens*
Radar · unrated1/4 core tests · not enough evidenceDeepSeek-V3.2 (Thinking)
arcee-ai

Trinity Mini

Models
Context window
131,072 tokens
Maximum output
131,072 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
arcee-ai

Trinity Nano Preview

Models
Context window
131,072 tokens
Maximum output
131,072 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence

* Provisional data