benchr
Worth reading
GPT-6 Astra: staged access and a 272K price cliff
GPT-6 Astra brings a 1.05M-token context window and a new long-context price tier. Check access and the 272K threshold before budgeting a migration.
Explore documented AI capabilities
Sourced capabilities, source-linked model records, and your own tests — in one place.
One clear model decision
Compare → test → choose.
Three steps. No universal winner.
01
CompareRead the recordPrice · context · sources
02
TestUse your own casesBlind scores · real outputs
03
ChooseSave the shortlistFit · cost · evidence
36source-linked models
25logged changes
41retirement records
4 labelsevidence categories
New and changed
Recent model updates
LoadingReading the source-checked change record…
Latest
View every release →-
01
GPT-6 Astra: staged access and a 272K price cliff
GPT-6 Astra brings a 1.05M-token context window and a new long-context price tier. Check access and the 272K threshold before budgeting a migration.
-
02
DeepSeek raised prices and made the clock part of the bill
DeepSeek raised V4 API prices on August 16, 2026 and split every rate into peak and off-peak halves. V4-Flash output went from $0.28 to $1.32 during peak hours.
-
03
Gemini 3.7 Flash costs the same as 3.6 Flash — and both double in January
Gemini 3.7 Flash went GA on August 13, 2026 at $0.75/$3.75 per 1M tokens, the same rate 3.6 Flash was cut to. Both return to $1.50/$7.50 on January 1, 2027.
-
04
GLM-5.3: 1M coding, hosted now with weights pending
Z.AI's API release adds post-training gains, always-on reasoning, and three compatible protocols at $1.40/$4.40.
-
05
Gemini 3.7 Flash: introductory pricing and migration
Google's stable multimodal model starts at $0.75/$3.75 through 2026, with a 1M-token window and a dated price change.
-
06
Grok 4.6: 500K agent model with no numeric output ceiling
xAI targets long coding runs and interactive agents at $2/$6, while its docs publish no numeric text-output cap.
-
07
Grok 4.5, reviewed: the coding specialist that got smaller, not bigger
Grok 4.5 review: xAI's coding specialist, built with Cursor, priced at $2/$6, with a smaller 500K context window than Grok 4.3 despite what some blogs claim.
-
08
GLM-5.2, reviewed: an open-weight model with a real coding claim
GLM-5.2 review: Zhipu's MIT-licensed, open-weight 753B model at $1.40/$4.40 per million tokens, with coding benchmarks Z.AI says beat GPT-5.5 and Opus 4.7.
Reviews
-
07
Claude Opus 5
Anthropic's current Opus at the same $5/$25 rate — what changes over 4.8, and who should move.
-
08
GPT-5
A candidate for visual and structured-output work based on OpenAI's published positioning; validate it on your own prompts.
-
09
Gemini 3 Pro
A retired multimodal model that Google deprecated in March 2026 in favor of Gemini 3.1 Pro.
Comparisons
-
10
Coding assistants
Cursor, GitHub Copilot, Windsurf, and Cody on the same Markdown-exporter task.
-
11
Voice models
ElevenLabs, OpenAI Whisper, and Cartesia Sonic on latency, accuracy, and naturalness.
-
12
Context windows
Advertised context capacity versus reproducible retrieval checks you can run on your own documents.
Analysis
-
13
Price per use case
The cheapest model for chat, coding, RAG, agents, classification, and summarization.
-
14
The open-weight tier
Where Llama 4, Mistral Large 3, DeepSeek-V4, and Qwen 3.6 stand against the closed labs.
-
15
Why benchmarks stopped telling you
MMLU is saturated above 90%. The benchmarks worth tracking now.
Guides
-
16
Frontier models
Claude Opus 4.7, GPT-5, and Gemini 3.1 Pro Preview: sourced specifications, editorial tradeoffs, and a local evaluation plan.
-
17
Open-weight models
Llama 4, Mistral, DeepSeek, Qwen, the small-model tier, and what it takes to self-host.
-
18
AI costs
What AI costs by model and workload, and where teams overspend.
Compare models directly
An interactive comparison covering source-linked pricing, named benchmark records, context windows, and documented capabilities for all 36 models in the shared index.
All 36 factual model records, sortable by published fields →
All 114 articles in the archive →
Provider guides: OpenAI, Anthropic, Google, and open weights →
benchr is an evidence-led reference, not a generic listicle. Figures are identified as official provider data, third-party benchmark results, or benchr editorial estimates so readers can judge the evidence behind each claim.
- Traceable evidence. Official prices and specifications link to provider documentation; benchmark results link to their maintainers; estimates and analysis are labeled as such. Verification dates and source fields are published in our open data file.
- A record no one else keeps. An append-only price history and a permanent deprecation register; retired models are never deleted — that memory is the point.
- Editorially independent and commercially transparent. Some marked links to AI/ML API, Lovable, and RunPod can earn benchr a commission without changing your price. Partners do not buy rankings or approve coverage. Google AdSense may be added only after approval. Read the affiliate disclosure, editorial standards, and corrections policy.