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-5.3 Chat (latest)

Models
Context window
128,000 tokens
Maximum output
16,384 tokens
Open weights
No
Reasoning
No
Arena 1388.9Human preference · 34,345 votes
alibaba

Qwen3.5 2B

Models
Context window
262,144 tokens
Maximum output
81,920 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen3.5 4B

Models
Context window
262,144 tokens
Maximum output
81,920 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen3.5-0.8B

Models
Context window
262,144 tokens
Maximum output
81,920 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen3.5 9B Base

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
google

Nano Banana 2 Preview

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

Qwen3.5 35B-A3B Base

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
liquid

LFM2 24B A2B

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

Mercury 2

Models
Context window
128,000 tokens
Maximum output
50,000 tokens
Open weights
No
Maximum input
128,000 tokens*
Arena 1354.8Human preference · 3,191 votes
alibaba

Qwen3.5 9B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen3.5 122B-A10B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
Arena 1417.5Human preference · 29,712 votes
alibaba

Qwen3.5 27B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
AI2D_TEST · version unreported · reported score92.90*Platform unreported
Arena 1409.0Human preference · 28,647 votes
alibaba

Qwen3.5 35B-A3B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
AI2D_TEST · version unreported · reported score92.60*Platform unreported
Arena 1394.5Human preference · 30,427 votes
alibaba

Qwen3.5 Flash

Models
Context window
1,000,000 tokens
Maximum output
65,536 tokens
Open weights
No
Reasoning
Yes
Arena 1397.1Human preference · 61,776 votes
google

Gemini 3.1 Pro Preview

Models
Context window
1,048,576 tokens
Maximum output
65,536 tokens
Open weights
No
Maximum input
1,048,576 tokens*
Arena 1480.1Human preference · 132,547 votes
google

Gemini 3.1 Pro Preview Custom Tools

Models
Context window
1,048,576 tokens
Maximum output
65,536 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
trendyol

Trendyol Asure 12B

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

Gemini 3.1 Pro

Models
Open weights
No*
Declared context window
1.05M*
Model type
LLM (multimodal)*
Declared modalities
Text, Image, Audio, Video → Text*
Reported score · version unreported · intelligence46.50*Platform unreported
ECI 155.2*General capability index
sarvam

Sarvam 105B

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

Sarvam 30B

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

Tiny Aya Earth

Models
Context window
8,000 tokens
Maximum output
8,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
cohere

Tiny Aya Fire

Models
Context window
8,000 tokens
Maximum output
8,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
cohere

Tiny Aya Global

Models
Context window
8,000 tokens
Maximum output
8,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence

* Provisional data