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
anthropic

Claude 3 Opus

Models
Open weights
No*
ECI 125.6*General capability index
anthropic

Claude 3 Sonnet

Models
Open weights
No*
ECI 119.6*General capability index
mistral

Mistral Large

Models
Context window
128,000 tokens
Maximum output
102,400 tokens
Open weights
No
Reasoning
No
ECI 120.0*General capability index
nvidia

Nemotron-4 15B

Models
Open weights
No*
ECI 99.6*General capability index
hugging face,servicenow,nvidia,bigcode

StarCoder 2 3B

Models
Open weights
Yes*
ECI 67.4*General capability index
google

gemma-2b

Models
Open weights
Yes
Model license
gemma
Checkpoint tensor payload
4.67 GiB
ECI 76.4*General capability index
google

gemma-7b

Models
Open weights
Yes
Model license
gemma
Checkpoint tensor payload
15.90 GiB
ECI 103.5*General capability index
hugging face,servicenow,nvidia,bigcode

StarCoder 2 15B

Models
Open weights
Yes*
ECI 96.7*General capability index
hugging face,servicenow,nvidia,bigcode

StarCoder 2 7B

Models
Open weights
Yes*
ECI 73.1*General capability index
baai

BGE M3

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

Qwen Plus

Models
Context window
1,000,000 tokens
Maximum output
32,768 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
alibaba

Qwen-VL Plus

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

Sonar

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Open weights
No
Maximum input
128,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
perplexity

Sonar Pro

Models
Context window
200,000 tokens
Maximum output
8,192 tokens
Open weights
No
Maximum input
200,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
perplexity

Sonar Reasoning Pro

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Open weights
No
Maximum input
128,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
google

Gemini 1.0 Pro

Models
Radar · unrated1/4 core tests · not enough evidencegemini-1.0-pro-001
microsoft

phi-2

Models
Context window
2,048 tokens
Total parameters
2.78 B
Open weights
Yes
Model license
mit
ECI 96.7*General capability index
upstage

SOLAR 10.7B Instruct v1.0

Models
Context window
4,096 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Arena 1083.1Human preference · 4,155 votes
mistral

Mixtral 8x7B Instruct v0.1

Models
Context window
32,768 tokens
Maximum output
32,768 tokens
Open weights
Yes
Maximum input
32,000 tokens*
Arena 1131.5Human preference · 73,503 votes
mistral

Mistral Embed

Models
Context window
8,000 tokens
Maximum output
3,072 tokens
Open weights
No
Maximum input
8,192 tokens*
Radar · unrated0/4 core tests · not enough evidence
mistral

Mixtral 8x7B

Models
Open weights
Yes*
ECI 113.4*General capability index
deepseek

deepseek-llm-67b-chat

Models
Context window
4,096 tokens
Open weights
Yes
Model license
other
Architecture
llama
Arena 1105.0Human preference · 4,932 votes

* Provisional data