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
6,274 results
rekaai

Reka Flash 3

Models
Context window
65,536 tokens
Maximum output
58,982 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
thedrummer

Skyfall 36B V2

Models
Context window
32,768 tokens
Maximum output
29,491 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
alibaba

QwQ 32B

Models
Context window
131,072 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
Yes
ECI 136.5*General capability index
alibaba

QwQ Plus

Models
Context window
131,072 tokens
Maximum output
8,192 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
cohere

Aya Vision 32B

Models
Context window
16,000 tokens
Maximum output
4,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
cohere

Aya Vision 8B

Models
Context window
16,000 tokens
Maximum output
4,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
cohere

Command R7B Arabic

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

GPT-4.5

Models
Open weights
No*
ECI 136.5*General capability index
microsoft

Phi-4-multimodal-instruct

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

Phi-4-mini

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
anthropic

Claude 3.7 Sonnet

Models
Open weights
No*
ECI 141.0*General capability index
anthropic

Claude Sonnet 3.7

Models
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No
Reasoning
Yes
Arena 1299.4Human preference · 42,572 votes
mistral

Saba

Models
Context window
32,768 tokens
Maximum output
26,214 tokens
Open weights
No
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
minimax

MiniMax image-01

Models
Open weights
No
Reasoning
No
Tool calling
No
Radar · unrated0/4 core tests · not enough evidence
google

Gemini 2.0 Pro

Models
Open weights
No*
ECI 135.3*General capability index
aion-labs

Aion-RP 1.0 (8B)

Models
Context window
32,768 tokens
Maximum output
29,491 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
perplexity

Sonar Deep Research

Models
Context window
128,000 tokens
Maximum output
32,768 tokens
Open weights
No
Maximum input
128,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Mistral Small 3

Models
Context window
32,768 tokens
Maximum output
16,384 tokens
Open weights
Yes
Reasoning
No
Arena 1233.5Human preference · 14,681 votes
alibaba

Qwen2.5-VL 72B Instruct

Models
Context window
131,072 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen2.5-Max

Models
Model license
Proprietary
ECI 131.2*General capability index
sdaia

ALLaM-2-7b

Models
Context window
4,096 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
deepseek

DeepSeek-R1-Distill-Qwen-32B

Models
Context window
131,072 tokens
Maximum output
32,768 tokens
Total parameters
32.76 B
Open weights
Yes
Radar · unrated1/4 core tests · not enough evidenceDeepSeek-R1-Distill-Qwen-32B

* Provisional data