Insights
Deep dives and practical guides on LLM performance, pricing changes, and new model comparisons.(51 posts)
Stay in the loop
Reviewed LLM analysis when a new edition is ready. No spam.
Gemini 3.1 Pro holds at $4.50 while GPT-5.5 variants fragment the top tier
Weekly LLM briefing: GPT-5.5 leads quality but three effort tiers muddy the picture. Gemini 3.1 Pro stays the value play. Kimi K2.6 undercuts everyone.
Which LLM for math, reasoning, and complex problem-solving in May 2026?
A practical guide to choosing the best LLM for math and reasoning tasks, with specific model picks at every price point.
The $4.50 model that makes Claude Opus 4.7 irrelevant for most workloads
Gemini 3.1 Pro Preview matches Claude Opus 4.7 quality at less than half the price with double the throughput. Here's what that means operationally.
GPT-5.5 takes the quality crown at $11.25, but the real action is at the bottom of the table
GPT-5.5 leads quality at 60.2 but costs 8x more than Kimi K2.6. This week's briefing breaks down who should care.
Which LLM for coding and software development in May 2026?
Practical guide to choosing the best LLM for coding workloads in May 2026, comparing GPT-5.5, GPT-5.3-Codex, Gemini 3.1 Pro, and budget options.
GPT-5.4 sits in no-man's land: too expensive to be cheap, too weak to justify the premium
OpenAI's GPT-5.4 scores 56.8 quality at $5.63/M tokens. Gemini 3.1 Pro nearly matches it for 20% less. A pricing analysis.
Gemini 3.1 Pro matches Claude Opus 4.7 quality at less than half the price
Google's Gemini 3.1 Pro Preview closes to within 0.1 points of Claude Opus 4.7 while costing $4.50 vs $10.00/M tokens. Plus: Grok 4.3 emerges as the speed-value pick.
Which LLM for budget-conscious teams spending under $1/M tokens in May 2026?
Practical guide to choosing the best LLM under $1/M tokens. DeepSeek V4 Pro leads on price, Kimi K2.6 wins on quality. Decision table included.
GPT-5.5's reasoning tiers cost the same $11.25/M tokens but deliver very different results
GPT-5.5 high and medium reasoning modes share a price tag but diverge by 2.2 quality points. When does the gap matter?
GPT-5.5 opens a 3-point quality gap, Gemini 3.1 Pro undercuts everyone above it
GPT-5.5 leads at 60.2 quality but costs $11.25/M tokens. Gemini 3.1 Pro matches Opus 4.7 at under half the price. Weekly LLM briefing for April 27.
Which LLM should you pick for coding and software development in April 2026?
Practical guide to choosing the best LLM for coding workloads in April 2026, with benchmarks, pricing, and decision tables.
Kimi K2.6 scores 53.9 at $1.48/M tokens — and that changes who you should call for mid-tier workloads
Kimi K2.6 from MoonshotAI delivers near-GPT-5.3-Codex quality at less than a third the price. We break down when it wins and when it doesn't.