Skip to content
trending
$ ls -t posts/

LATEST_

All posts in reverse chronological order

[595] October 2026

FLUX 3 Image: resolution tests, layout control, editing and prices
Benchmarks

FLUX 3 Image: resolution tests, layout control, editing and prices

8 min read
Meta Muse Image: Price, Availability & Test Results
Benchmarks

Meta Muse Image: Price, Availability & Test Results

7 min read

[596] September 2026

Meta Muse Spark 1.3: Benchmarks, Pricing and Test Results
Benchmarks

Meta Muse Spark 1.3: Benchmarks, Pricing and Test Results

8 min read
I Tested Claude Fable 5.1 - One Task Froze It
Benchmarks

I Tested Claude Fable 5.1 - One Task Froze It

5 min read
GPT-6 Astra Benchmarks: Three Tests Where It Loses
Benchmarks

GPT-6 Astra Benchmarks: Three Tests Where It Loses

4 min read
GPT-6 Astra Test: Non-English Writing, Code, 150K Context
Benchmarks

GPT-6 Astra Test: Non-English Writing, Code, 150K Context

4 min read
Imagen 3 vs Imagen 3 Fast vs DALL-E 3: 6-Task Test
Benchmarks

Imagen 3 vs Imagen 3 Fast vs DALL-E 3: 6-Task Test

5 min read
GPT-6 Astra Hallucination Test: Fake Facts vs Real Ones
Benchmarks

GPT-6 Astra Hallucination Test: Fake Facts vs Real Ones

3 min read
Claude vs GPT-6: Polish Text Costs 56% More Tokens
Benchmarks

Claude vs GPT-6: Polish Text Costs 56% More Tokens

2 min read
GPT-6 Astra for Coding: What the Benchmarks Show (and Hide)
Benchmarks

GPT-6 Astra for Coding: What the Benchmarks Show (and Hide)

2 min read
ChatGPT Images 2.5 vs 2.0: What Actually Changed
Benchmarks

ChatGPT Images 2.5 vs 2.0: What Actually Changed

2 min read
ChatGPT Image Editing Test: 11 Edits, 11 Unwanted Changes
Benchmarks

ChatGPT Image Editing Test: 11 Edits, 11 Unwanted Changes

5 min read
Qwen3.8 Max Test: 13 Tasks, Scores, Pricing & Access
Benchmarks

Qwen3.8 Max Test: 13 Tasks, Scores, Pricing & Access

5 min read
GLM 5.3 Real Cost: Three Numbers Don’t Match the Model Card
Benchmarks

GLM 5.3 Real Cost: Three Numbers Don’t Match the Model Card

7 min read
I Built an AI Test for 11 Models. One Task Had a Bug
Benchmarks

I Built an AI Test for 11 Models. One Task Had a Bug

6 min read
How Much Does an AI-Generated Article Cost? I Paid and Counted
Benchmarks

How Much Does an AI-Generated Article Cost? I Paid and Counted

5 min read
AI Context Window Test: Two Models Failed at 25,000 Tokens
Benchmarks

AI Context Window Test: Two Models Failed at 25,000 Tokens

5 min read
New AI Models Force Reasoning On - 7 of 18 Won’t Let You Disable
Benchmarks

New AI Models Force Reasoning On - 7 of 18 Won’t Let You Disable

4 min read
I Asked 6 AI Models 8 Biology Questions. Zero Refusals
Benchmarks

I Asked 6 AI Models 8 Biology Questions. Zero Refusals

3 min read
LLM Confidence Scales: 0-20 Works Better Than 0-100
Benchmarks

LLM Confidence Scales: 0-20 Works Better Than 0-100

3 min read
PIDS-Bench: Why Prompt Injection Detectors Fail in Real Use
Benchmarks

PIDS-Bench: Why Prompt Injection Detectors Fail in Real Use

2 min read
AI Agent Consistency: IBM Research Tackles the Reliability Gap
Benchmarks

AI Agent Consistency: IBM Research Tackles the Reliability Gap

2 min read
AI Model Refuses to Read Documents: Testing Three Providers
Benchmarks

AI Model Refuses to Read Documents: Testing Three Providers

6 min read
Qwen-Image-2.1 Alpha Channel: Native Transparent PNG Test
Benchmarks

Qwen-Image-2.1 Alpha Channel: Native Transparent PNG Test

5 min read
// site map

Content

Models

Prices and data

Trackers and law

Learn

Tools and more

Quantslant in numbers 1,427posts in archive26news from the last 7 days18video models in the observatory
🎬 AI Video Benchmarks: Higgsfield DoP vs OpenAI Sora • Higgsfield vs Runway Gen-3 • AI Video Credit Calculator
× ‹ enlarge ›