#benchmarks
10 articles
- 2026-10-25
The Agent Benchmark Is Also a Log-Integrity Test
Inspect AI's latest repairs show why ranking agents requires trustworthy failure and recovery records, not just more tasks.
- 2026-10-17
Tokens Per Second Is Two Benchmarks Wearing a Trench Coat
A single tokens-per-second score hides prompt ingestion, decoding, and the workload that actually matters. Benchmark both halves or stop comparing machines.
- 2026-10-13
Decision Models Are Eating Chat Models' Lunch
Cloudflare, Amazon, and Jev all shipped open decision models in October 2026. The question isn't which is best — it's why you'd use a chat model for routing in 2026.
- 2026-04-04
Gemma 4 26B: Google Drops a MoE Monster With 4B Active Params
Google DeepMind released Gemma 4 today. The 26B A4B MoE scores 1441 on LMArena while burning just 4B active parameters. Here's what that means for local inference.
- 2026-03-20
Mistral Small 4: A 119B Model That Fits in 70GB and Actually Runs Fast
Mistral Small 4 is a 119B MoE model with only 6B active parameters. I ran it on AMD Strix Halo hardware and got real numbers.
- 2026-03-07
MiniMax M2.5: When Frontier Intelligence Gets Cheap Enough to Leave Running All Night
- 2026-03-05
Which Local LLMs Can Actually Use Tools?
I ran a 15-test tool-calling benchmark against every local model on my Ryzen AI Max+ 395. The results were not what I expected.
- 2026-03-01
I Tested 10 AI Models So You Don't Have To
A weekend spent benchmarking every promising local AI model on consumer hardware. Here's what actually works.
- 2026-02-26
Bigger Isn't Better: How a 9GB Model Beat 120B Parameters
I benchmarked 17 local LLMs across 13 dimensions with 39 tests. The results destroyed my assumptions about model size.
- 2026-02-23
GPT-OSS 120B: First Benchmarks on Consumer AMD Hardware
Real benchmarks of OpenAI's open-weight 120B MoE model running on a Ryzen AI Max+ 395 with 128GB unified memory. No cloud, no A100s, just bare metal.