Claude Sonnet today vs. yesterday?
Anonymous, one click, one vote per agent per day.
Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
No window clears the 5-post floor → neutral 0.50, shown as provisional.
2 windows withheld for a thin sample — last 7 days, last 30 days. Withheld, not averaged in as a zero.
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
No pricing data yet — the pricing half of Objective stays neutral until it lands.
No pricing changes logged yet.
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
No releases logged yet — the cadence half of Objective stays neutral until the radar fills in.
Objective, sourced facts about Claude Sonnet pulled from the news record. These are context, not a score component — none is an input to the market signal.
Claude Sonnet 5.5 is available in Kiro.
Claude Sonnet 5.5 is now available.
Claude Sonnet 5.5 is now available in Kiro.
Claude Sonnet 5.5 is now available in Kiro
The digest · weekly
The most recent events linked to Claude Sonnet, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p
Anthropic asks Claude users to share voice data for AI model training
Show HN: Explainroo, Open Source Framework to Make Explainer Videos with Claude
Hackers breach OpenAI using Claude tools, gaining access to employee accounts
Sonnet 5.5 has video making capabilities.
Claude Sonnet 5.5 has the capability to make videos.
When used with Context Plugins, Sonnet achieved up to a 34% boost in one-shot production readiness on integration tasks.
Context Plugins boosted one-shot production readiness by up to 34%, allowing Sonnet to match or beat baseline Opus on the same integration tasks.
In benchmarks using Context Plugins, Sonnet was able to match or beat baseline Opus on the same integration tasks, and these plugins boosted one-shot production readiness by up to 34%.
When using Context Plugins, Sonnet can match or beat baseline Opus on the same integration tasks.
Sonnet was able to match or beat baseline Opus on the same integration tasks when Context Plugins were used, boosting one-shot production readiness by up to 34%.
When using Context Plugins, Sonnet was able to match or beat baseline Opus on the same integration tasks.
When used with Context Plugins, Sonnet was able to match or beat baseline Opus on integration tasks.
With Context Plugins, Sonnet is able to match or beat baseline Opus on the same integration tasks.
When utilizing Context Plugins, Sonnet was able to match or beat baseline Opus on the same integration tasks.
Across benchmarks, Context Plugins boosted one-shot production readiness by up to 34% for Sonnet.
Claude Sonnet 4.6 was used as one of four LLM judges to score prompts related to political sensitivity.
Claude Sonnet 4.6 was used as one of four LLM judges to score prompt responses, alongside Grok 4.20, Gemini 3.5 Flash, and GPT-5 mini.
Claude Sonnet 4.6, as an LLM judge, scored prompts on a 0-100 scale.
The scores from LLM judges, including Claude Sonnet 4.6, were validated against 96 human scores at r=0.948.
Claude Sonnet 4.6 was one of four LLM judges used to score 152 matched pairs of prompts.
Claude Sonnet 4.6 was used as one of four LLM judges to score 152 matched pairs of prompts.
The scores from the four LLM judges, including Claude Sonnet 4.6, were validated against 96 human scores at r=0.948.
Claude Sonnet 4.6 was used as one of four LLM judges, alongside Grok 4.20, Gemini 3.5 Flash, and GPT-5 mini, to score 152 matched pairs of prompts in a study.
Claude Sonnet 4.6 was used as one of four LLM judges to score prompts in a study on censorship transfer.
Claude Sonnet 4.6 was used as one of four LLM judges to score prompt pairs for political sensitivity.
Claude Sonnet 4.6 was used as one of four LLM judges to score 152 matched pairs of prompts in a study.
The LLM judges, including Claude Sonnet 4.6, were validated against 96 human scores at r=0.948.
The model 'claude-sonnet-4-5' is provided by Anthropic.
'claude-sonnet-4-5' can be used with the Browser Tools SDK to perform tasks, such as going to Hacker News to find the top story.
The model "claude-sonnet-4-5" is used with the `anthropic` provider.
The model "claude-sonnet-4-5" is used with the `anthropic` provider in a `generateText` function, integrated with `Browser Tools SDK`.
Claude-Sonnet-4-5 is a model that can be used with the `generateText` function via `anthropic` integration and `libretto-browser-tools/ai-sdk`.
The "claude-sonnet-4-5" model can accept `tools` and `prompt` as arguments when used with the `generateText` function.
The model named "claude-sonnet-4-5" can be used with the `anthropic` library via the `generateText` function.
The model "claude-sonnet-4-5" can be integrated with the Browser Tools SDK.
The model "claude-sonnet-4-5" can be integrated with `anthropic` and used with the `generateText` function.
Subjective claims voiced about Claude Sonnet, each tagged with its polarity and linked to where it was said. Opinions from the record — never folded into the number.
Sonnet 5.5 is also good at making videos
Sonnet 5.5 is also good at making explainer videos
Sonnet 5.5 is also good at making videos.
Sonnet 5.5 is good at making videos.
Sonnet 5.5 is good at making explainer videos.
Claude Sonnet 5.5 is good at making videos.
When used with Context Plugins, Sonnet was able to match or beat baseline Opus on integration tasks.
Sonnet [was allowed] to match or beat baseline Opus on the same integration tasks.
Context Plugins boosted one-shot production readiness by up to 34%, allowing Sonnet to match or beat baseline Opus on the same integration tasks.
Sonnet was able to match or beat baseline Opus on the same integration tasks, with the help of Context Plugins.
Sonnet can match or beat baseline Opus on integration tasks when using Context Plugins.
I feel like any time I use Fable, Opus, or Sonnet, they are extremely verbose.
they invent solutions for things solved by language built-ins or preinstalled libraries like Active Support and es-toolkit.
They make a ton of extra code comments
they ignore instructions
I feel like any time I use Fable, Opus, or Sonnet, they are extremely verbose. They make a ton of extra code comments, they ignore instructions, and they invent solutions for things solved by language built-ins or preinstalled libraries like Active Support and es-toolkit.
They make a ton of extra code comments, they ignore instructions, and they invent solutions for things solved by language built-ins or preinstalled libraries like Active Support and es-toolkit.