Name: Claude 3.5 Sonnet Released
Author: Anthropic

Claude 3.5 Sonnet Released · Chronopin

AIPosted 09/28/202609/28/2026 at 8:59 pm

To timeline

Anthropic

Starts 06/20/2024

San Francisco, California, United States

To map

Thread

Respond to this Pin

GPQA Diamond (0-shot CoT)%

Claude 3 Opus50.4
GPT-4o53.6
Claude 3.5 Sonnet59.4

source

MMLU (5-shot)%

Gemini 1.5 Pro85.9
Llama-400b (early snapshot)86.1
Claude 3 Opus86.8
Claude 3.5 Sonnet88.7

source

HumanEval (0-shot)%

Gemini 1.5 Pro84.1
Llama-400b (early snapshot)84.1
Claude 3 Opus84.9
GPT-4o90.2
Claude 3.5 Sonnet92

source

DROP (F1, 3-shot)F1

Claude 3 Opus83.1
GPT-4o83.4
Claude 3.5 Sonnet87.1

source

BIG-Bench-Hard (3-shot CoT)%

Claude 3 Opus86.8
Gemini 1.5 Pro89.2
Claude 3.5 Sonnet93.1

source

Claude 3.5 Sonnet specs as launched

Spec	Value
Maker	Anthropic^[1][2]
Context window	200K tokens

Language model rubric2026 criteria

Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Scored as launched (Claude 3.5 Sonnet, 20 Jun 2024): 200K-token context and $3 in / $15 out per 1M tokens = $6 blended at 3:1 (both from Anthropic's announcement); text and image input. Anthropic said it runs at twice the speed of Claude 3 Opus but gave no tokens/s, so speed null. Reasoning null: no launch-version Artificial Analysis Intelligence Index entry was opened (AA now shows re-based v4.1 scores); Anthropic's headline GPQA/MMLU/HumanEval figures have no anchor. Coding null (no Terminal-Bench 4.0). Reviews: Willison, Zvi, TechCrunch, The Decoder, Synthedia; these are launch-week analyses with some first-hand use (Willison, Zvi), not systematic tests.

Alternate names

Claude 3.5
Alias

User Photos

Photos from readers, kept apart from the pin's sourced media. Rate what you ate or saw, and on a restaurant pin tag the dishes right on your photo.

Comments

References 585% CONFIDENCEOverall confidence: 85%How well the pin's source and references back up its dates.Weighted average of how firmly 5 references, the source included, support the pin's start and end times; a reference counts half as much for every 180 days older than the newestShow all pins at 75% confidence or better

The first entry is always the pin's source. Overall confidence is a weighted average of how firmly each reference supports the start and end times used above; a reference counts half as much for every 180 days older than the newest.

[1]90%
anthropic.com/news/claude-3-5-sonnet
anthropic.com· Posted Sep 28, 2026· Starts Jun 20, 2024· 32% of score
Anthropic^[2]: "Today, we're launching Claude 3.5 Sonnet" and it "is now available for free on Claude.ai"; the page header now shows Jun 21, 2024, but TechCrunch^[4] and AWS both published the launch on 20 June 2024 and the model ID is claude-3-5-sonnet-20240620.
[2]90%
Claude 3.5 Sonnet Model Card Addendum
www-cdn.anthropic.com· Added Sep 28, 2026· 32% of score
Anthropic's^[1] model card addendum: 59.4% on GPQA Diamond, 88.7% on MMLU (5-shot), 92.0% on HumanEval, 71.1% on MATH and 68.3% on MMMU, against Claude 3 Opus's 50.4%, 86.8%, 84.9%, 60.1% and 59.4%; 64% on the internal agentic coding evaluation against Opus's 38%.
[3]75%
Claude (AI) - Wikipedia
en.wikipedia.org· Added Sep 28, 2026· 32% of score
"On June 20, 2024, Anthropic^[1][2] released Claude 3.5 Sonnet, which, according to the company's own benchmarks, performed better than the larger Claude 3 Opus", alongside Artifacts, which previews code, SVG graphics or websites in a separate window.
[4]92%
Anthropic claims its latest model is best-in-class
techcrunch.com· Published Jun 20, 2024· Starts Jun 20, 2024 ✓· 1% of score
TechCrunch, published 2024-06-20T14:00Z: Anthropic^[1][2] "is releasing a powerful new generative AI model called Claude 3.5 Sonnet", about twice the speed of Claude 3 Opus, alongside Artifacts. It dates the launch 20 June, where Anthropic's own header now shows the 21 June UTC timestamp.
[5]90%
Anthropic's Claude 3.5 Sonnet model now available in Amazon Bedrock: Even more intelligence than Claude 3 Opus at one-fifth the cost
aws.amazon.com· Published Jun 20, 2024· Starts Jun 20, 2024· 1% of score
AWS News Blog, 20 JUN 2024: "Today, Anthropic^[1][2] introduced Claude 3.5 Sonnet ... now available in Amazon Bedrock"; 80 percent cheaper than Opus and about 10 percent better than Claude 3 Opus on most vision benchmarks.

Suggest a correction

Something missing or wrong? Say it in your own words: a link that backs this pin up, a different start or end date and why, or a fact it lacks or gets wrong. The AI checks it against this pin's sources, searches for better ones, and adds any page that backs you up. The pin's own sources still count most. A picture that shows something else, or shows it badly, is looked at too, and moved down or replaced.

Reviews

Claude 3.5 Sonnet · simonwillison.net · Jun 20, 2024Anthropic released a new model this morning, and I think it's likely now the single best available LLM.
On Claude 3.5 Sonnet · thezvi.substack.com · Jun 24, 2024There is a new clear best (non-tiny) LLM. If you want to converse with an LLM, the correct answer is Claude Sonnet 3.5.
Anthropic claims its latest model is best-in-class · techcrunch.com · Jun 20, 2024But it's more an incremental step than a monumental leap forward.
Anthropic launches Claude 3.5, potentially the most capable AI model yet · the-decoder.com · Jun 20, 2024This makes Sonnet 3.5 potentially the most powerful model available today - at the same price as its predecessor.
Anthropic Sonnet 3.5 Sets New Benchmark Standards · synthedia.substack.com · Jun 21, 2024Claude 3.5's Sonnet is "more intelligent" than Claude 3's Opus, and it delivers this quality at a far lower price point.

Sentiment over timePositive

Sentiment

Sentiment over time
Claude 3.5 Sonnet · Jun 20, 2024	0.90
Anthropic claims its latest model is best-in-class · Jun 20, 2024	0.20
Anthropic launches Claude 3.5, potentially the most capable AI model yet · Jun 20, 2024	0.80
Anthropic Sonnet 3.5 Sets New Benchmark Standards · Jun 21, 2024	0.80
On Claude 3.5 Sonnet · Jun 24, 2024	0.90

"Today, we're launching Claude 3.5 Sonnet—our first release in the forthcoming Claude 3.5 model family", which outperforms Claude 3 Opus "with the speed and cost of our mid-tier model, Claude 3 Sonnet"^[1][4]
Free on Claude.ai and the Claude iOS app, with higher rate limits for Pro and Team subscribers, and available the same day on the Anthropic API, Amazon Bedrock and Google Cloud's Vertex AI^[1][5]
It launched with Artifacts, a window beside the conversation where code, documents and website designs appear so users can see, edit and build on them in real time^[1][3]
It remained at ASL-2; Anthropic gave it to the UK AI Safety Institute for pre-deployment testing, which shared the results with the US AI Safety Institute^[1]
Anthropic said it would complete the family with Claude 3.5 Haiku and Claude 3.5 Opus later in 2024^[1]

Notable features

Priced at $3 per million input tokens and $15 per million output tokens, with a 200K-token context window; AWS calls it 80 percent cheaper than Claude 3 Opus^[1][5]
Runs at twice the speed of Claude 3 Opus^[1][4]
Anthropic's model card: 59.4% on GPQA Diamond, 88.7% on MMLU, 92.0% on HumanEval and 71.1% on MATH, against Claude 3 Opus's 50.4%, 86.8%, 84.9% and 60.1%^[2]
It solved 64% of problems in an internal agentic coding evaluation - fixing a bug or adding a feature to an open-source codebase - against 38% for Claude 3 Opus^[1][2]
Anthropic's strongest vision model yet: better at reading charts and graphs and transcribing text from imperfect images, scoring 68.3% on MMMU^[1][2]

Benchmarks^[1]

Benchmark	Claude 3.5 Sonnet	Claude 3 Opus	GPT-4o	Gemini 1.5 Pro	Llama-400b (early snapshot)
Graduate level reasoning (GPQA, Diamond)	59.4%* (0-shot CoT)	50.4% (0-shot CoT)	53.6% (0-shot CoT)	—	—
Undergraduate level knowledge (MMLU), 5-shot	88.7%** (5-shot)	86.8% (5-shot)	—	85.9% (5-shot)	86.1% (5-shot)
Undergraduate level knowledge (MMLU), 0-shot CoT	88.3% (0-shot CoT)	85.7% (0-shot CoT)	88.7% (0-shot CoT)	—	—
Code (HumanEval)	92.0% (0-shot)	84.9% (0-shot)	90.2% (0-shot)	84.1% (0-shot)	84.1% (0-shot)
Multilingual math (MGSM)	91.6% (0-shot CoT)	90.7% (0-shot CoT)	90.5% (0-shot CoT)	87.5% (8-shot)	—
Reasoning over text (DROP, F1 score)	87.1 (3-shot)	83.1 (3-shot)	83.4 (3-shot)	74.9 (variable shots)	83.5 (3-shot, pre-trained model)
Mixed evaluations (BIG-Bench-Hard)	93.1% (3-shot CoT)	86.8% (3-shot CoT)	—	89.2% (3-shot CoT)	85.3% (3-shot CoT, pre-trained model)
Math problem-solving (MATH)	71.1% (0-shot CoT)	60.1% (0-shot CoT)	76.6% (0-shot CoT)	67.7% (4-shot)	57.8% (4-shot CoT)
Grade school math (GSM8K)	96.4% (0-shot CoT)	95.0% (0-shot CoT)	—	90.8% (11-shot)	94.1% (8-shot CoT)

* Claude 3.5 Sonnet scores 67.2% on 5-shot CoT GPQA with maj@32. ** Claude 3.5 Sonnet scores 90.4% on MMLU with 5-shot CoT prompting.

Suggest a correction

Comments

Reviews

Sentiment over timePositive

Claude 3.5 Sonnet Released

Notable features

Benchmarks^[1]

Training

Tags

Thread

Suggest a correction

Comments

Reviews

Sentiment over timePositive

Claude 3.5 Sonnet Released

Notable features

Benchmarks[1]

Training

Tags

Thread

Benchmarks^[1]