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
openai

GPT-4o (2024-11-20)

Models
Context window
128,000 tokens
Maximum output
16,384 tokens
Open weights
No
Reasoning
No
Radar · unrated1/4 core tests · not enough evidenceGPT-4o (Nov 2024)
openai

GPT-4o (Nov 2024)

Models
Open weights
No*
ECI 128.9*General capability index
mistral

Mistral Large 2.1

Models
Context window
131,072 tokens
Maximum output
16,384 tokens
Open weights
Yes
Reasoning
No
Arena 1265.3Human preference · 28,073 votes
alibaba

Qwen2.5-Coder-32B-Instruct

Models
Context window
131,072 tokens
Maximum output
8,192 tokens
Total parameters
32.76 B
Open weights
Yes
Arena 1230.0Human preference · 5,432 votes
alibaba

Qwen2.5-Coder-0.5B

Models
Context window
32,768 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
thedrummer

UnslopNemo 12B

Models
Context window
1,024,000 tokens
Maximum output
819,200 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
mistral

Mistral Large (latest)

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

Pixtral Large (latest)

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

Qwen Turbo

Models
Context window
1,000,000 tokens
Maximum output
16,384 tokens
Open weights
No
Reasoning
Yes
Radar · unrated1/4 core tests · not enough evidenceqwen-turbo-2024-11-01
cohere

Aya Expanse 32B

Models
Context window
128,000 tokens
Maximum output
4,000 tokens
Open weights
Yes
Reasoning
No
Arena 1224.0Human preference · 27,124 votes
cohere

Aya Expanse 8B

Models
Context window
8,000 tokens
Maximum output
4,000 tokens
Open weights
Yes
Reasoning
No
Arena 1185.1Human preference · 9,818 votes
anthropic

Claude Haiku 3.5

Models
Context window
200,000 tokens
Maximum output
8,192 tokens
Open weights
No
Reasoning
No
Arena 1255.4Human preference · 69,061 votes
anthropic

Claude Sonnet 3.5 v2

Models
Context window
200,000 tokens
Maximum output
8,192 tokens
Open weights
No
Reasoning
No
Arena 1297.8Human preference · 87,769 votes
anthracite-org

Magnum v4 72B

Models
Context window
32,768 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
anthropic

Claude 3.5 Haiku

Models
Open weights
No*
ECI 125.0*General capability index
mistral

Ministral 3B

Models
Context window
128,000 tokens
Maximum output
8,192 tokens
Open weights
Yes
Reasoning
No
Radar · unrated1/4 core tests · not enough evidenceministral-3b-2410
mistral

Ministral 8B Instruct

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

Palmyra X4

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
openai

Whisper Large v3 Turbo

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

Llama 3.2 1B Instruct

Models
Context window
131,072 tokens
Maximum output
32,000 tokens
Open weights
Yes
Reasoning
No
Arena 1054.6Human preference · 8,045 votes
meta

Llama-3.2-11B-Vision-Instruct

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
meta

Llama-3.2-1B

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

Llama-3.2-3B

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

* Provisional data