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
6,271 results
alibaba

Qwen MT Plus

Models
Context window
16,384 tokens
Maximum output
8,192 tokens
Open weights
No
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen3 Coder Plus

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

Qwen3-Coder 480B-A35B Instruct

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
No
Arena 1356.6Human preference · 25,190 votes
alibaba

Qwen3 235B-A22B Instruct 2507

Models
Context window
262,144 tokens
Maximum output
16,384 tokens
Total parameters
235.09 B
Open weights
Yes
Arena 1419.1Human preference · 98,134 votes
mistral

Voxtral Mini 3B 2507

Models
Context window
32,768 tokens
Maximum output
32,768 tokens
Open weights
Yes
Maximum input
32,768 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Voxtral Small 24B 2507

Models
Context window
32,768 tokens
Maximum output
32,768 tokens
Open weights
Yes
Maximum input
32,768 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Voxtral Small (latest)

Models
Context window
32,000 tokens
Maximum output
32,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
moonshotai

Kimi K2 (Jul 2025)

Models
Open weights
Yes*
ECI 141.3*General capability index
moonshotai

Kimi K2 Instruct

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

Kimi K2 0711

Models
Context window
131,072 tokens
Maximum output
98,304 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Devstral Medium

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

Devstral Small

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

Uncensored

Models
Context window
128,000 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
xai

Grok 4

Models
Context window
256,000 tokens*
Open weights
No*
Model type
Large language model (reasoning)*
Declared modalities
Text + image input, text output*
ECI 146.9*General capability index
morph

Morph V3 Fast

Models
Context window
262,144 tokens
Maximum output
131,072 tokens
Open weights
No
Maximum input
16,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
morph

Morph V3 Large

Models
Context window
262,144 tokens
Maximum output
131,072 tokens
Open weights
No
Maximum input
16,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
ai21

Jamba Large

Models
Context window
256,000 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
baidu

ERNIE 4.5 21B A3B

Models
Context window
131,072 tokens
Maximum output
8,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
baidu

ERNIE 4.5 300B A47B

Models
Context window
131,072 tokens
Maximum output
12,000 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
baidu

ERNIE 4.5 VL 424B A47B

Models
Context window
123,000 tokens
Maximum output
16,000 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
google

gemma-3n-E2B-it

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

gemma-3n-E4B-it

Models
Context window
32,768 tokens
Maximum output
32,768 tokens
Open weights
Yes
Reasoning
No
Arena 1305.6Human preference · 22,136 votes
openai

o3-deep-research

Models
Context window
200,000 tokens
Maximum output
100,000 tokens
Open weights
No
Maximum input
200,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
openai

o4-mini-deep-research

Models
Context window
200,000 tokens
Maximum output
100,000 tokens
Open weights
No
Maximum input
200,000 tokens*
Radar · unrated0/4 core tests · not enough evidence

* Provisional data