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 2

Models
Open weights
No*
ECI 117.3*General capability index
salesforce

XGen-7B

Models
Open weights
Yes*
ECI 71.0*General capability index
mosaicml

MPT-30B

Models
Open weights
Yes*
ECI 85.8*General capability index
openai

GPT-4 (Jun 2023)

Models
Open weights
No*
ECI 120.2*General capability index
tii

falcon-40b

Models
Open weights
Yes
Model license
apache-2.0
Checkpoint tensor payload
77.93 GiB
Architecture
falcon
ECI 91.2*General capability index
mosaicml

MPT-7B

Models
Open weights
Yes*
ECI 74.2*General capability index
tii

falcon-7b

Models
Open weights
Yes
Model license
apache-2.0
Checkpoint tensor payload
13.44 GiB
Architecture
falcon
ECI 73.9*General capability index
databricks

Dolly 2.0-12b

Models
Open weights
Yes*
ECI 56.4*General capability index
cerebras systems

Cerebras-GPT-13B

Models
Open weights
Yes*
ECI 49.9*General capability index
openai

GPT-4 (Mar 2023)

Models
Open weights
No*
ECI 121.9*General capability index
openai

GPT-3.5-turbo

Models
Context window
16,385 tokens
Maximum output
4,096 tokens
Open weights
No
Maximum input
16,385 tokens*
Radar · unrated0/4 core tests · not enough evidence
meta

LLaMA-13B

Models
Model license
Non-commercial
ECI 85.8*General capability index
meta

LLaMA-33B

Models
Open weights
Yes*
ECI 97.0*General capability index
meta

LLaMA-65B

Models
Open weights
Yes*
ECI 102.0*General capability index
meta

LLaMA-7B

Models
Open weights
Yes*
ECI 77.9*General capability index
Unspecified

gpt-5.6

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-luna

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-luna-2026-07-09

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-sol

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-sol-2026-07-09

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-terra

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

azure/gpt-5.6-terra-2026-07-09

Models*
Maximum output
128,000 tokens*
Maximum input
922,000 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence
Unspecified

gemini/gemini-3.1-flash-lite

Models*
Maximum output
65,536 tokens*
Maximum input
1,048,576 tokens*
Reasoning
Yes*
Tool calling
Yes*
Radar · unrated0/4 core tests · not enough evidence

* Provisional data