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
6,278 results
openai

GPT-Image-1.5

Models
Open weights
No
Reasoning
No
Tool calling
No
API mode
Image generation*
Radar · unrated0/4 core tests · not enough evidence
anthropic

Claude Opus 4.5

Models
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No
Maximum input
200,000 tokens*
Arena 1450.9Human preference · 72,899 votes
anthropic

Claude Opus 4.5 (latest)

Models
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No
Reasoning
Yes
Radar · unrated3/4 core tests · not enough evidenceClaude Opus 4.5 (32k thinking)
google

Nano Banana Pro Preview

Models
Context window
65,536 tokens
Maximum output
32,768 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
xai

Grok 4.1 Fast (Reasoning)

Models
Context window
2,000,000 tokens
Maximum output
30,000 tokens
Open weights
No
Reasoning
Yes
Arena 1407.9Human preference · 57,500 votes
xai

Grok 4.1 Fast

Models
Context window
2,000,000 tokens
Maximum output
30,000 tokens
Open weights
No
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
google

Gemini 3 Pro Preview

Models
Context window
1,048,576 tokens
Maximum output
65,536 tokens
Open weights
No
Reasoning
Yes
Radar · unrated1/4 core tests · not enough evidenceGemini 3 Pro Preview
google

Gemini 3 Pro

Models
Model license
Proprietary
ECI 153.2*General capability index
openai

GPT-5.1

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
272,000 tokens*
ECI 149.9*General capability index
openai

GPT-5.1 Chat

Models
Context window
128,000 tokens
Maximum output
16,384 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
openai

GPT-5.1 Codex

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
400,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
openai

GPT-5.1 Codex Max

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
400,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
openai

GPT-5.1 Codex mini

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
400,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
moonshotai

Kimi K2 Thinking

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
Yes
ECI 145.9*General capability index
moonshotai

Kimi K2 Thinking Turbo

Models
Context window
262,144 tokens
Maximum output
262,144 tokens
Open weights
Yes
Reasoning
Yes
Arena 1414.4Human preference · 63,310 votes
openai

GPT OSS Safeguard 120B

Models
Context window
131,072 tokens
Maximum output
32,768 tokens
Open weights
Yes
Maximum input
128,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
openai

GPT OSS Safeguard 20B

Models
Context window
131,072 tokens
Maximum output
131,072 tokens
Open weights
Yes
Maximum input
128,000 tokens*
Radar · unrated0/4 core tests · not enough evidence
nvidia

Llama 3.1 Nemotron Safety Guard 8B v3

Models
Context window
128,000 tokens
Maximum output
4,096 tokens
Total parameters
8.03 B
Open weights
Yes
Radar · unrated0/4 core tests · not enough evidence
nvidia

Nemotron Nano 12B v2 VL

Models
Context window
128,000 tokens
Maximum output
128,000 tokens
Open weights
Yes
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
minimax

MiniMax-M2

Models
Context window
204,800 tokens
Maximum output
131,072 tokens
Open weights
Yes
Maximum input
Reported value 1: 200,000 tokens*
Reported value 2: 1,000,000 tokens*
Arena 1340.1Human preference · 6,850 votes
nvidia

Llama Nemotron Embed 1B v2

Models
Context window
8,192 tokens
Maximum output
2,048 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
paddlepaddle

PaddleOCR VL

Models
Context window
131,072 tokens
Maximum output
16,384 tokens
Open weights
Yes
Reasoning
No
Radar · unrated0/4 core tests · not enough evidence
openai

GPT-5 Image Mini

Models
Context window
400,000 tokens
Maximum output
128,000 tokens
Open weights
No
Reasoning
Yes
Radar · unrated0/4 core tests · not enough evidence
anthropic

Claude Haiku 4.5

Models
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No
Maximum input
200,000 tokens*
Reported score · version unreported · intelligence37*Platform unreported
Arena 1396.6Human preference · 149,199 votes

* Provisional data