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
6,269 results
openai

GPT-6.1 Terra

Models
Context window
1,050,000 tokens
Maximum output
128,000 tokens
Open weights
No
Reasoning
Yes
ECI 168.1*General capability index
moonshotai

Kimi K3.1 Pro

Models
Context window
1,048,576 tokens
Maximum output
131,072 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
recursive

Flint

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

MiniMax-M3.1-Flash

Models
Context window
1,000,000 tokens
Maximum output
512,000 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
deepseek

DeepSeek V4.1 Flash 1017

Models
Context window
1,000,000 tokens
Maximum output
384,000 tokens
Open weights
Yes
Reasoning
Yes
ECI 158.8*General capability index
inception

Mercury 3

Models
Context window
1,000,000 tokens
Maximum output
131,072 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
meta

Muse Spark Open

Models
Context window
1,048,576 tokens
Maximum output
131,072 tokens
Open weights
Yes
Reasoning
Yes
ECI 155.1*General capability index
nvidia

Nemotron 3.5 Super 120B A12B

Models
Context window
1,048,576 tokens
Maximum output
131,072 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
nvidia

Nemotron 3.5 Super VL 120B A12B

Models
Context window
1,048,576 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
xai

Grok Voice 3.0

Models
Open weights
No
Reasoning
Yes
Tool calling
Yes
Input modalities
text / audio
Radar · unrated0/4 core tests · not enough evidence
typesafe

Jev 1.14

Models
Context window
64,000 tokens
Open weights
No
Reasoning
No
Tool calling
No
Radar · unrated0/4 core tests · not enough evidence
google

Gemini 4 Argon

Models
Context window
1,048,576 tokens
Maximum output
65,536 tokens
Open weights
No
Reasoning
Yes
Arena 1528.6Human preference · 11,889 votes
meta

Muse Wonder

Models
Context window
1,048,576 tokens
Maximum output
131,072 tokens
Open weights
No
Reasoning
Yes
ECI 161.7*General capability index
meta

Muse Wonder Full

Models
Context window
1,048,576 tokens
Open weights
No
Reasoning
Yes
Tool calling
Yes
Radar · unrated0/4 core tests · not enough evidence
lightonai

LightOnOCR-3 0.8B

Models
Context window
262,144 tokens
Maximum output
16,384 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
phocinae

Phocinae Largha 150M v1

Models
Context window
8,192 tokens
Open weights
Yes
Reasoning
No
Tool calling
No
Radar · unrated0/4 core tests · not enough evidence
anthropic

Claude Haiku 5.5

Models
Context window
1,000,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
1,000,000 tokens*
ECI 160.4*General capability index
openbmb

MiniCPM-V 4.7 35B-A3B

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
nace-ai

Drex 2.0

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

MiniCPM-V 4.7 1B

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

Mistral Large 4

Models
Context window
1,048,576 tokens
Maximum output
262,144 tokens
Open weights
No
Maximum input
1,048,576 tokens*
ECI 150.6*General capability index
google

Nano Banana 2.1

Models
Context window
131,072 tokens
Maximum output
32,768 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
reflection

Beam 1.0 501B A23B

Models
Context window
1,048,576 tokens
Maximum output
131,072 tokens
Open weights
Yes
Reasoning
Yes
Arena 1425.4Human preference · 4,233 votes
reflection

Beam 1.0

Models
ECI 150.2*General capability index

* Provisional data