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
6,293 results
microsoft

MediPhi-Guidelines

Models
Context window
131,072 tokens
Total parameters
3.82 B
Open weights
Yes
Model license
mit
Radar · unrated0/4 core tests · not enough evidence
microsoft

MediPhi-Instruct

Models
Context window
131,072 tokens
Total parameters
3.82 B
Open weights
Yes
Model license
mit
Radar · unrated0/4 core tests · not enough evidence
microsoft

MediPhi-MedCode

Models
Context window
131,072 tokens
Total parameters
3.82 B
Open weights
Yes
Model license
mit
Radar · unrated0/4 core tests · not enough evidence
microsoft

MediPhi-PubMed

Models
Context window
131,072 tokens
Total parameters
3.82 B
Open weights
Yes
Model license
mit
Radar · unrated0/4 core tests · not enough evidence
Unspecified

meta_llama/Llama-3.3-70B-Instruct

Models*
Maximum output
4,028 tokens*
Maximum input
128,000 tokens*
Tool calling
Yes*
API mode
Chat*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

meta_llama/Llama-3.3-8B-Instruct

Models*
Maximum output
4,028 tokens*
Maximum input
128,000 tokens*
Tool calling
Yes*
API mode
Chat*
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3-70B

Models
Context window
8,192 tokens
Total parameters
70.55 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3-70B-Instruct

Models
Context window
8,192 tokens
Total parameters
70.55 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3-8B

Models
Context window
8,192 tokens
Total parameters
8.03 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3-8B-Alternate-Tokenizer

Models
Context window
8,192 tokens
Total parameters
8.03 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3-8B-Instruct

Models
Context window
8,192 tokens
Total parameters
8.03 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3.1-70B

Models
Context window
131,072 tokens
Total parameters
70.55 B
Open weights
Yes
Model license
llama3.1
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3.1-70B-Instruct

Models
Context window
131,072 tokens
Total parameters
70.55 B
Open weights
Yes
Model license
llama3.1
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3.1-8B

Models
Context window
131,072 tokens
Total parameters
8.03 B
Open weights
Yes
Model license
llama3.1
Radar · unrated0/4 core tests · not enough evidence
nousresearch

Meta-Llama-3.1-8B-Instruct

Models
Context window
131,072 tokens
Total parameters
8.03 B
Open weights
Yes
Model license
llama3.1
Radar · unrated0/4 core tests · not enough evidence
mistral

Mistral-7B-Instruct-v0.1

Models
Context window
32,768 tokens
Total parameters
7.24 B
Open weights
Yes
Model license
apache-2.0
Radar · unrated0/4 core tests · not enough evidence
mistral

Mistral-7B-Instruct-v0.2

Models
Context window
32,768 tokens
Maximum output
4,096 tokens*
Total parameters
7.24 B
Open weights
Yes
Arena 1089.5Human preference · 19,402 votes
nvidia

Mistral-NeMo-Minitron-8B-Base

Models
Context window
8,192 tokens
Total parameters
8.41 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
nvidia

Mistral-NeMo-Minitron-8B-Instruct

Models
Context window
8,192 tokens
Total parameters
8.41 B
Open weights
Yes
Model license
other
Radar · unrated0/4 core tests · not enough evidence
Unspecified

mistral.mistral-large-2407-v1:0

Models*
Maximum output
8,191 tokens*
Maximum input
128,000 tokens*
Tool calling
Yes*
API mode
Chat*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

mistral.pixtral-large-2502-v1:0

Models*
Maximum output
16,384 tokens*
Maximum input
128,000 tokens*
Tool calling
Yes*
API mode
Chat*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

nebius/deepseek-ai/DeepSeek-R1

Models*
Maximum output
128,000 tokens*
Maximum input
128,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence

* Provisional data