Simon Willison's Weblog: llm

Gemini 3.1 Flash-Lite

2026-03-03T21:53:54+00:00

Google's latest model is an update to their inexpensive Flash-Lite family. At $0.25/million tokens of input and $1.5/million output this is 1/8th the price of Gemini 3.1 Pro.

It supports four different thinking levels, so I had it output four different pelicans:

minimal

low

medium

high

Tags: gemini, llm, pelican-riding-a-bicycle, llm-pricing, ai, llms, llm-release, google, generative-ai

Gemini 3.1 Pro

2026-02-19T17:58:37+00:00

Gemini 3.1 Pro

The first in the Gemini 3.1 series, priced the same as Gemini 3 Pro ($2/million input, $12/million output under 200,000 tokens, $4/$18 for 200,000 to 1,000,000). That's less than half the price of Claude Opus 4.6 with very similar benchmark scores to that model.

They boast about its improved SVG animation performance compared to Gemini 3 Pro in the announcement!

I tried "Generate an SVG of a pelican riding a bicycle" in Google AI Studio and it thought for 323.9 seconds (thinking trace here) before producing this one:

It's good to see the legs clearly depicted on both sides of the frame (should satisfy Elon), the fish in the basket is a nice touch and I appreciated this comment in the SVG code:

<!-- Black Flight Feathers on Wing Tip -->
<path d="M 420 175 C 440 182, 460 187, 470 190 C 450 210, 430 208, 410 198 Z" fill="#374151" />

I've added the two new model IDs gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools to my llm-gemini plugin for LLM. That "custom tools" one is described here - apparently it may provide better tool performance than the default model in some situations.

The model appears to be incredibly slow right now - it took 104s to respond to a simple "hi" and a few of my other tests met "Error: This model is currently experiencing high demand. Spikes in demand are usually temporary. Please try again later." or "Error: Deadline expired before operation could complete" errors. I'm assuming that's just teething problems on launch day.

It sounds like last week's Deep Think release was our first exposure to the 3.1 family:

Last week, we released a major update to Gemini 3 Deep Think to solve modern challenges across science, research and engineering. Today, we’re releasing the upgraded core intelligence that makes those breakthroughs possible: Gemini 3.1 Pro.

Update: In What happens if AI labs train for pelicans riding bicycles? last November I said:

If a model finally comes out that produces an excellent SVG of a pelican riding a bicycle you can bet I’m going to test it on all manner of creatures riding all sorts of transportation devices.

Google's Gemini Lead Jeff Dean tweeted this video featuring an animated pelican riding a bicycle, plus a frog on a penny-farthing and a giraffe driving a tiny car and an ostrich on roller skates and a turtle kickflipping a skateboard and a dachshund driving a stretch limousine.

I've been saying for a while that I wish AI labs would highlight things that their new models can do that their older models could not, so top marks to the Gemini team for this video.

Update 2: I used llm-gemini to run my more detailed Pelican prompt, with this result:

From the SVG comments:

<!-- Pouch Gradient (Breeding Plumage: Red to Olive/Green) -->
...
<!-- Neck Gradient (Breeding Plumage: Chestnut Nape, White/Yellow Front) -->

Tags: gemini, llm, pelican-riding-a-bicycle, ai, llms, llm-release, google, generative-ai, svg

llm-gemini 0.29

2026-02-19T17:57:25+00:00

Release: llm-gemini 0.29

LLM plugin to access Google's Gemini family of models

Tags: llm, gemini

Introducing Claude Sonnet 4.6

2026-02-17T23:58:58+00:00

Introducing Claude Sonnet 4.6

Sonnet 4.6 is out today, and Anthropic claim it offers similar performance to November's Opus 4.5 while maintaining the Sonnet pricing of $3/million input and $15/million output tokens (the Opus models are $5/$25). Here's the system card PDF.

Sonnet 4.6 has a "reliable knowledge cutoff" of August 2025, compared to Opus 4.6's May 2025 and Haiku 4.5's February 2025. Both Opus and Sonnet default to 200,000 max input tokens but can stretch to 1 million in beta and at a higher cost.

I just released llm-anthropic 0.24 with support for both Sonnet 4.6 and Opus 4.6. Claude Code did most of the work - the new models had a fiddly amount of extra details around adaptive thinking and no longer supporting prefixes, as described in Anthropic's migration guide.

Here's what I got from:

uvx --with llm-anthropic llm 'Generate an SVG of a pelican riding a bicycle' -m claude-sonnet-4.6

The SVG comments include:

<!-- Hat (fun accessory) -->

I tried a second time and also got a top hat. Sonnet 4.6 apparently loves top hats!

For comparison, here's the pelican Opus 4.5 drew me in November:

And here's Anthropic's current best pelican, drawn by Opus 4.6 on February 5th:

Opus 4.6 produces the best pelican beak/pouch. I do think the top hat from Sonnet 4.6 is a nice touch though.

Via Hacker News

Tags: llm, anthropic, claude, llm-pricing, ai, llms, llm-release, generative-ai, pelican-riding-a-bicycle, claude-code

llm-anthropic 0.24

2026-02-17T23:51:23+00:00

Release: llm-anthropic 0.24

LLM access to models by Anthropic, including the Claude series

Tags: llm, claude, anthropic

datasette-llm 0.1a0

2026-01-22T17:10:06+00:00

Release: datasette-llm 0.1a0

LLM integration plugin for other plugins to depend on

Tags: datasette, llm

jordanhubbard/nanolang

2026-01-19T23:58:56+00:00

jordanhubbard/nanolang

Plenty of people have mused about what a new programming language specifically designed to be used by LLMs might look like. Jordan Hubbard (co-founder of FreeBSD, with serious stints at Apple and NVIDIA) just released exactly that.

A minimal, LLM-friendly programming language with mandatory testing and unambiguous syntax.

NanoLang transpiles to C for native performance while providing a clean, modern syntax optimized for both human readability and AI code generation.

The syntax strikes me as an interesting mix between C, Lisp and Rust.

I decided to see if an LLM could produce working code in it directly, given the necessary context. I started with this MEMORY.md file, which begins:

Purpose: This file is designed specifically for Large Language Model consumption. It contains the essential knowledge needed to generate, debug, and understand NanoLang code. Pair this with spec.json for complete language coverage.

I ran that using LLM and llm-anthropic like this:

llm -m claude-opus-4.5 \
  -s https://raw.githubusercontent.com/jordanhubbard/nanolang/refs/heads/main/MEMORY.md \
  'Build me a mandelbrot fractal CLI tool in this language' 
  > /tmp/fractal.nano

The resulting code... did not compile.

I may have been too optimistic expecting a one-shot working program for a new language like this. So I ran a clone of the actual project, copied in my program and had Claude Code take a look at the failing compiler output.

... and it worked! Claude happily grepped its way through the various examples/ and built me a working program.

Here's the Claude Code transcript - you can see it reading relevant examples here - and here's the finished code plus its output.

I've suspected for a while that LLMs and coding agents might significantly reduce the friction involved in launching a new language. This result reinforces my opinion.

Via Hacker News

Tags: coding-agents, ai-assisted-programming, programming-languages, claude-code, generative-ai, ai, llms, llm

llm-gemini 0.28.2

2025-12-23T16:20:33+00:00

Release: llm-gemini 0.28.2

LLM plugin to access Google's Gemini family of models

Tags: llm, gemini

llm-gemini 0.28.1

2025-12-18T17:57:28+00:00

Release: llm-gemini 0.28.1

LLM plugin to access Google's Gemini family of models

Tags: llm, gemini

Gemini 3 Flash

2025-12-17T22:44:52+00:00

It continues to be a busy December, if not quite as busy as last year. Today's big news is Gemini 3 Flash, the latest in Google's "Flash" line of faster and less expensive models.

Google are emphasizing the comparison between the new Flash and their previous generation's top model Gemini 2.5 Pro:

Building on 3 Pro’s strong multimodal, coding and agentic features, 3 Flash offers powerful performance at less than a quarter the cost of 3 Pro, along with higher rate limits. The new 3 Flash model surpasses 2.5 Pro across many benchmarks while delivering faster speeds.

Gemini 3 Flash's characteristics are almost identical to Gemini 3 Pro: it accepts text, image, video, audio, and PDF, outputs only text, handles 1,048,576 maximum input tokens and up to 65,536 output tokens, and has the same knowledge cut-off date of January 2025 (also shared with the Gemini 2.5 series).

The benchmarks look good. The cost is appealing: 1/4 the price of Gemini 3 Pro ≤200k and 1/8 the price of Gemini 3 Pro >200k, and it's nice not to have a price increase for the new Flash at larger token lengths.

It's a little more expensive than previous Flash models - Gemini 2.5 Flash was $0.30/million input tokens and $2.50/million on output, Gemini 3 Flash is $0.50/million and $3/million respectively.

Google claim it may still end up cheaper though, due to more efficient output token usage:

> Gemini 3 Flash is able to modulate how much it thinks. It may think longer for more complex use cases, but it also uses 30% fewer tokens on average than 2.5 Pro.

Here's a more extensive price comparison on my llm-prices.com site.

Generating some SVGs of pelicans

I released llm-gemini 0.28 this morning with support for the new model. You can try it out like this:

llm install -U llm-gemini
llm keys set gemini # paste in key
llm -m gemini-3-flash-preview "Generate an SVG of a pelican riding a bicycle"

According to the developer docs the new model supports four different thinking level options: minimal, low, medium, and high. This is different from Gemini 3 Pro, which only supported low and high.

You can run those like this:

llm -m gemini-3-flash-preview --thinking-level minimal "Generate an SVG of a pelican riding a bicycle"

Here are four pelicans, for thinking levels minimal, low, medium, and high:

I built the gallery component with Gemini 3 Flash

The gallery above uses a new Web Component which I built using Gemini 3 Flash to try out its coding abilities. The code on the page looks like this:

<image-gallery width="4">
    <img src="https://static.simonwillison.net/static/2025/gemini-3-flash-preview-thinking-level-minimal-pelican-svg.jpg" alt="A minimalist vector illustration of a stylized white bird with a long orange beak and a red cap riding a dark blue bicycle on a single grey ground line against a plain white background." />
    <img src="https://static.simonwillison.net/static/2025/gemini-3-flash-preview-thinking-level-low-pelican-svg.jpg" alt="Minimalist illustration: A stylized white bird with a large, wedge-shaped orange beak and a single black dot for an eye rides a red bicycle with black wheels and a yellow pedal against a solid light blue background." />
    <img src="https://static.simonwillison.net/static/2025/gemini-3-flash-preview-thinking-level-medium-pelican-svg.jpg" alt="A minimalist illustration of a stylized white bird with a large yellow beak riding a red road bicycle in a racing position on a light blue background." />
    <img src="https://static.simonwillison.net/static/2025/gemini-3-flash-preview-thinking-level-high-pelican-svg.jpg" alt="Minimalist line-art illustration of a stylized white bird with a large orange beak riding a simple black bicycle with one orange pedal, centered against a light blue circular background." />
</image-gallery>

Those alt attributes are all generated by Gemini 3 Flash as well, using this recipe:

llm -m gemini-3-flash-preview --system '
You write alt text for any image pasted in by the user. Alt text is always presented in a
fenced code block to make it easy to copy and paste out. It is always presented on a single
line so it can be used easily in Markdown images. All text on the image (for screenshots etc)
must be exactly included. A short note describing the nature of the image itself should go first.' \
-a https://static.simonwillison.net/static/2025/gemini-3-flash-preview-thinking-level-high-pelican-svg.jpg

You can see the code that powers the image gallery Web Component here on GitHub. I built it by prompting Gemini 3 Flash via LLM like this:

llm -m gemini-3-flash-preview '
Build a Web Component that implements a simple image gallery. Usage is like this:

<image-gallery width="5">
  <img src="image1.jpg" alt="Image 1">
  <img src="image2.jpg" alt="Image 2" data-thumb="image2-thumb.jpg">
  <img src="image3.jpg" alt="Image 3">
</image-gallery>

If an image has a data-thumb= attribute that one is used instead, other images are scaled down. 

The image gallery always takes up 100% of available width. The width="5" attribute means that five images will be shown next to each other in each row. The default is 3. There are gaps between the images. When an image is clicked it opens a modal dialog with the full size image.

Return a complete HTML file with both the implementation of the Web Component several example uses of it. Use https://picsum.photos/300/200 URLs for those example images.'

It took a few follow-up prompts using llm -c:

llm -c 'Use a real modal such that keyboard shortcuts and accessibility features work without extra JS'

llm -c 'Use X for the close icon and make it a bit more subtle'

llm -c 'remove the hover effect entirely'

llm -c 'I want no border on the close icon even when it is focused'

Here's the full transcript, exported using llm logs -cue.

Those five prompts took:

225 input, 3,269 output
2,243 input, 2,908 output
4,319 input, 2,516 output
6,376 input, 2,094 output
8,151 input, 1,806 output

Added together that's 21,314 input and 12,593 output for a grand total of 4.8436 cents.

The guide to migrating from Gemini 2.5 reveals one disappointment:

Image segmentation: Image segmentation capabilities (returning pixel-level masks for objects) are not supported in Gemini 3 Pro or Gemini 3 Flash. For workloads requiring native image segmentation, we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5.

I wrote about this capability in Gemini 2.5 back in April. I hope they come back in future models - they're a really neat capability that is unique to Gemini.

Tags: gemini, llm, pelican-riding-a-bicycle, llm-pricing, ai, llms, llm-release, generative-ai, google, web-components

llm-gemini 0.28

2025-12-17T18:14:48+00:00

Release: llm-gemini 0.28

LLM plugin to access Google's Gemini family of models

Tags: llm, gemini

LLM 0.28

2025-12-12T20:20:14+00:00

LLM 0.28

I released a new version of my LLM Python library and CLI tool for interacting with Large Language Models. Highlights from the release notes:

New OpenAI models: gpt-5.1, gpt-5.1-chat-latest, gpt-5.2 and gpt-5.2-chat-latest. #1300, #1317

When fetching URLs as fragments using llm -f URL, the request now includes a custom user-agent header: llm/VERSION (https://llm.datasette.io/). #1309

Fixed a bug where fragments were not correctly registered with their source when using llm chat. Thanks, Giuseppe Rota. #1316

Fixed some file descriptor leak warnings. Thanks, Eric Bloch. #1313

Type annotations for the OpenAI Chat, AsyncChat and Completion execute() methods. Thanks, Arjan Mossel. #1315

The project now uses uv and dependency groups for development. See the updated contributing documentation. #1318

That last bullet point about uv relates to the dependency groups pattern I wrote about in a recent TIL. I'm currently working through applying it to my other projects - the net result is that running the test suite is as simple as doing:

git clone https://github.com/simonw/llm
cd llm
uv run pytest

The new dev dependency group defined in pyproject.toml is automatically installed by uv run in a new virtual environment which means everything needed to run pytest is available without needing to add any extra commands.

Tags: llm, uv, annotated-release-notes, ai, llms, python, generative-ai, projects

llm 0.28

2025-12-12T20:03:45+00:00

Release: llm 0.28

Access large language models from the command-line

Tags: llm

GPT-5.2

2025-12-11T23:58:04+00:00

OpenAI reportedly declared a "code red" on the 1st of December in response to increasingly credible competition from the likes of Google's Gemini 3. It's less than two weeks later and they just announced GPT-5.2, calling it "the most capable model series yet for professional knowledge work".

Key characteristics of GPT-5.2

The new model comes in two variants: GPT-5.2 and GPT-5.2 Pro. There's no Mini variant yet.

GPT-5.2 is available via their UI in both "instant" and "thinking" modes, presumably still corresponding to the API concept of different reasoning effort levels.

The knowledge cut-off date for both variants is now August 31st 2025. This is significant - GPT 5.1 and 5 were both Sep 30, 2024 and GPT-5 mini was May 31, 2024.

Both of the 5.2 models have a 400,000 token context window and 128,000 max output tokens - no different from 5.1 or 5.

Pricing wise 5.2 is a rare increase - it's 1.4x the cost of GPT 5.1, at $1.75/million input and $14/million output. GPT-5.2 Pro is $21.00/million input and a hefty $168.00/million output, putting it up there with their previous most expensive models o1 Pro and GPT-4.5.

So far the main benchmark results we have are self-reported by OpenAI. The most interesting ones are a 70.9% score on their GDPval "Knowledge work tasks" benchmark (GPT-5 got 38.8%) and a 52.9% on ARC-AGI-2 (up from 17.6% for GPT-5.1 Thinking).

The ARC Prize Twitter account provided this interesting note on the efficiency gains for GPT-5.2 Pro

A year ago, we verified a preview of an unreleased version of @OpenAI o3 (High) that scored 88% on ARC-AGI-1 at est. $4.5k/task

Today, we’ve verified a new GPT-5.2 Pro (X-High) SOTA score of 90.5% at $11.64/task

This represents a ~390X efficiency improvement in one year

GPT-5.2 can be accessed in OpenAI's Codex CLI tool like this:

codex -m gpt-5.2

There are three new API models:

gpt-5.2 - I think this is what you get if you select "GPT-5.2 Thinking" in ChatGPT but I'm a little confused.
gpt-5.2-chat-latest - the model used by ChatGPT for "GPT-5.2 Instant" mode. It's priced the same as GPT-5.2 but has a reduced 128,000 context window with 16,384 max output tokens.
gpt-5.2-pro

OpenAI have published a new GPT-5.2 Prompting Guide. An interesting note from that document is that compaction can now be run with a new dedicated server-side API:

For long-running, tool-heavy workflows that exceed the standard context window, GPT-5.2 with Reasoning supports response compaction via the /responses/compact endpoint. Compaction performs a loss-aware compression pass over prior conversation state, returning encrypted, opaque items that preserve task-relevant information while dramatically reducing token footprint. This allows the model to continue reasoning across extended workflows without hitting context limits.

It's better at vision

One note from the announcement that caught my eye:

GPT‑5.2 Thinking is our strongest vision model yet, cutting error rates roughly in half on chart reasoning and software interface understanding.

I had disappointing results from GPT-5 on an OCR task a while ago. I tried it against GPT-5.2 and it did much better:

llm -m gpt-5.2 ocr -a https://static.simonwillison.net/static/2025/ft.jpeg

Here's the result from that, which cost 1,520 input and 1,022 for a total of 1.6968 cents.

Rendering some pelicans

For my classic "Generate an SVG of a pelican riding a bicycle" test:

llm -m gpt-5.2 "Generate an SVG of a pelican riding a bicycle"

And for the more advanced alternative test, which tests instruction following in a little more depth:

llm -m gpt-5.2 "Generate an SVG of a California brown pelican riding a bicycle. The bicycle
must have spokes and a correctly shaped bicycle frame. The pelican must have its
characteristic large pouch, and there should be a clear indication of feathers.
The pelican must be clearly pedaling the bicycle. The image should show the full
breeding plumage of the California brown pelican."

Update 14th December 2025: I used GPT-5.2 running in Codex CLI to port a complex Python library to JavaScript. It ran without interference for nearly four hours and completed a complex task exactly to my specification.

Tags: llm, openai, pelican-riding-a-bicycle, ai, llms, llm-release, gpt-5, generative-ai

Devstral 2

2025-12-09T23:58:27+00:00

Devstral 2

Two new models from Mistral today: Devstral 2 and Devstral Small 2 - both focused on powering coding agents such as Mistral's newly released Mistral Vibe which I wrote about earlier today.

Devstral 2: SOTA open model for code agents with a fraction of the parameters of its competitors and achieving 72.2% on SWE-bench Verified.

Up to 7x more cost-efficient than Claude Sonnet at real-world tasks.

Devstral 2 is a 123B model released under a janky license - it's "modified MIT" where the modification is:

You are not authorized to exercise any rights under this license if the global consolidated monthly revenue of your company (or that of your employer) exceeds $20 million (or its equivalent in another currency) for the preceding month. This restriction in (b) applies to the Model and any derivatives, modifications, or combined works based on it, whether provided by Mistral AI or by a third party. [...]

Mistral Small 2 is under a proper Apache 2 license with no weird strings attached. It's a 24B model which is 51.6GB on Hugging Face and should quantize to significantly less.

I tried out the larger model via my llm-mistral plugin like this:

llm install llm-mistral
llm mistral refresh
llm -m mistral/devstral-2512 "Generate an SVG of a pelican riding a bicycle"

For a ~120B model that one is pretty good!

Here's the same prompt with -m mistral/labs-devstral-small-2512 for the API hosted version of Devstral Small 2:

Again, a decent result given the small parameter size. For comparison, here's what I got for the 24B Mistral Small 3.2 earlier this year.

Tags: llm-release, mistral, generative-ai, ai, janky-licenses, llms, llm, pelican-riding-a-bicycle

Introducing Mistral 3

2025-12-02T17:30:57+00:00

Introducing Mistral 3

Four new models from Mistral today: three in their "Ministral" smaller model series (14B, 8B, and 3B) and a new Mistral Large 3 MoE model with 675B parameters, 41B active.

All of the models are vision capable, and they are all released under an Apache 2 license.

I'm particularly excited about the 3B model, which appears to be a competent vision-capable model in a tiny ~3GB file.

Xenova from Hugging Face got it working in a browser:

@MistralAI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗

Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯

You can try that demo in your browser, which will fetch 3GB of model and then stream from your webcam and let you run text prompts against what the model is seeing, entirely locally.

Mistral's API hosted versions of the new models are supported by my llm-mistral plugin already thanks to the llm mistral refresh command:

$ llm mistral refresh
Added models: ministral-3b-2512, ministral-14b-latest, mistral-large-2512, ministral-14b-2512, ministral-8b-2512

I tried pelicans against all of the models. Here's the best one, from Mistral Large 3:

And the worst from Ministral 3B:

Tags: vision-llms, llm-release, mistral, llm, generative-ai, ai, llms

llm-templates-fabric 0.2.1

2025-11-26T04:56:15+00:00

Release: llm-templates-fabric 0.2.1

Load LLM templates from Fabric

Tags: llm

llm-anthropic 0.23

2025-11-25T05:26:34+00:00

llm-anthropic 0.23

New plugin release adding support for Claude Opus 4.5, including the new thinking_effort option:

llm install -U llm-anthropic
llm -m claude-opus-4.5 -o thinking_effort low 'muse on pelicans'

This took longer to release than I had hoped because it was blocked on Anthropic shipping 0.75.0 of their Python library with support for thinking effort.

Tags: llm, anthropic, claude, generative-ai, projects, ai, llms

llm-anthropic 0.23

2025-11-25T05:20:15+00:00

Release: llm-anthropic 0.23

LLM access to models by Anthropic, including the Claude series

Tags: llm, anthropic, claude

llm-anthropic 0.22

2025-11-19T15:15:36+00:00

Release: llm-anthropic 0.22

LLM access to models by Anthropic, including the Claude series

Tags: llm, claude, anthropic

llm-gemini 0.27

2025-11-18T23:00:40+00:00

llm-gemini 0.27

New release of my LLM plugin for Google's Gemini models:

Support for nested schemas in Pydantic, thanks Bill Pugh. #107

Now tests against Python 3.14.

Support for YouTube URLs as attachments and the media_resolution option. Thanks, Duane Milne. #112

New model: gemini-3-pro-preview. #113

The YouTube URL feature is particularly neat, taking advantage of this API feature. I used it against the Google Antigravity launch video:

llm -m gemini-3-pro-preview \
 -a 'https://www.youtube.com/watch?v=nTOVIGsqCuY' \
 'Summary, with detailed notes about what this thing is and how it differs from regular VS Code, then a complete detailed transcript with timestamps'

Here's the result. A spot-check of the timestamps against points in the video shows them to be exactly right.

Tags: gemini, llm, generative-ai, projects, ai, llms, youtube

llm-gemini 0.27

2025-11-18T22:56:18+00:00

Release: llm-gemini 0.27

LLM plugin to access Google's Gemini family of models

Tags: llm, gemini

Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark

2025-11-18T19:00:48+00:00

Google released Gemini 3 Pro today. Here's the announcement from Sundar Pichai, Demis Hassabis, and Koray Kavukcuoglu, their developer blog announcement from Logan Kilpatrick, the Gemini 3 Pro Model Card, and their collection of 11 more articles. It's a big release!

I had a few days of preview access to this model via AI Studio. The best way to describe it is that it's Gemini 2.5 upgraded to match the leading rival models.

Gemini 3 has the same underlying characteristics as Gemini 2.5. The knowledge cutoff is the same (January 2025). It accepts 1 million input tokens, can output up to 64,000 tokens, and has multimodal inputs across text, images, audio, and video.

Benchmarks

Google's own reported numbers (in the model card) show it scoring slightly higher against Claude 4.5 Sonnet and GPT-5.1 against most of the standard benchmarks. As always I'm waiting for independent confirmation, but I have no reason to believe those numbers are inaccurate.

Pricing

It terms of pricing it's a little more expensive than Gemini 2.5 but still cheaper than Claude Sonnet 4.5. Here's how it fits in with those other leading models:

Model	Input (per 1M tokens)	Output (per 1M tokens)
GPT-5.1	$1.25	$10.00
Gemini 2.5 Pro	≤ 200k tokens: $1.25 > 200k tokens: $2.50	≤ 200k tokens: $10.00 > 200k tokens: $15.00
Gemini 3 Pro	≤ 200k tokens: $2.00 > 200k tokens: $4.00	≤ 200k tokens: $12.00 > 200k tokens: $18.00
Claude Sonnet 4.5	≤ 200k tokens: $3.00 > 200k tokens: $6.00	≤ 200k tokens: $15.00 > 200k tokens: $22.50
Claude Opus 4.1	$15.00	$75.00

Trying it out against a complex image

That screenshot of the benchmarks from above looked like a good test for Gemini 3's multimodal support. I fed it that image URL and asked it to generate alt text for the image:

llm -m gemini-3-pro-preview -a https://static.simonwillison.net/static/2025/gemini-3-benchmarks.jpg 'Alt text for this image, include all figures and make them comprehensible to a screen reader user'

Here's what I got back:

A comprehensive table comparing four AI models across various performance benchmarks. The columns listed are: Benchmark Name, Description, Gemini 3 Pro (highlighted in blue), Gemini 2.5 Pro, Claude Sonnet 4.5, and GPT-5.1.

Humanity's Last Exam (Academic reasoning)

No tools: Gemini 3 Pro 37.5%, Gemini 2.5 Pro 21.6%, Claude Sonnet 4.5 13.7%, GPT-5.1 26.5%.

With search and code execution: Gemini 3 Pro 45.8% (others have no data).

ARC-AGI-2 (Visual reasoning puzzles; ARC Prize Verified)

Gemini 3 Pro 31.1%, Gemini 2.5 Pro 4.9%, Claude Sonnet 4.5 13.6%, GPT-5.1 17.6%.

GPQA Diamond (Scientific knowledge; No tools)

Gemini 3 Pro 91.9%, Gemini 2.5 Pro 86.4%, Claude Sonnet 4.5 83.4%, GPT-5.1 88.1%.

AIME 2025 (Mathematics)

No tools: Gemini 3 Pro 95.0%, Gemini 2.5 Pro 88.0%, Claude Sonnet 4.5 87.0%, GPT-5.1 94.0%.

With code execution: Gemini 3 Pro 100%, Claude Sonnet 4.5 100%.

MathArena Apex (Challenging Math Contest problems)

Gemini 3 Pro 23.4%, Gemini 2.5 Pro 0.5%, Claude Sonnet 4.5 1.6%, GPT-5.1 1.0%.

MMMU-Pro (Multimodal understanding and reasoning)

Gemini 3 Pro 81.0%, Gemini 2.5 Pro 68.0%, Claude Sonnet 4.5 68.0%, GPT-5.1 76.0%.

ScreenSpot-Pro (Screen understanding)

Gemini 3 Pro 72.7%, Gemini 2.5 Pro 11.4%, Claude Sonnet 4.5 36.2%, GPT-5.1 3.5%.

CharXiv Reasoning (Information synthesis from complex charts)

Gemini 3 Pro 81.4%, Gemini 2.5 Pro 69.6%, Claude Sonnet 4.5 68.5%, GPT-5.1 69.5%.

OmniDocBench 1.5 (OCR; Overall Edit Distance, lower is better)

Gemini 3 Pro 0.115, Gemini 2.5 Pro 0.145, Claude Sonnet 4.5 0.145, GPT-5.1 0.147.

Video-MMMU (Knowledge acquisition from videos)

Gemini 3 Pro 87.6%, Gemini 2.5 Pro 83.6%, Claude Sonnet 4.5 77.8%, GPT-5.1 80.4%.

LiveCodeBench Pro (Competitive coding problems; Elo Rating, higher is better)

Gemini 3 Pro 2,439; Gemini 2.5 Pro 1,775; Claude Sonnet 4.5 1,418; GPT-5.1 2,243.

Terminal-Bench 2.0 (Agentic terminal coding; Terminus-2 agent)

Gemini 3 Pro 54.2%, Gemini 2.5 Pro 32.6%, Claude Sonnet 4.5 42.8%, GPT-5.1 47.6%.

SWE-Bench Verified (Agentic coding; Single attempt)

Gemini 3 Pro 76.2%, Gemini 2.5 Pro 59.6%, Claude Sonnet 4.5 77.2%, GPT-5.1 76.3%.

t2-bench (Agentic tool use)

Gemini 3 Pro 85.4%, Gemini 2.5 Pro 54.9%, Claude Sonnet 4.5 84.7%, GPT-5.1 80.2%.

Vending-Bench 2 (Long-horizon agentic tasks; Net worth (mean), higher is better)

Gemini 3 Pro $5,478.16; Gemini 2.5 Pro $573.64; Claude Sonnet 4.5 $3,838.74; GPT-5.1 $1,473.43.

FACTS Benchmark Suite (Held out internal grounding, parametric, MM, and search retrieval benchmarks)

Gemini 3 Pro 70.5%, Gemini 2.5 Pro 63.4%, Claude Sonnet 4.5 50.4%, GPT-5.1 50.8%.

SimpleQA Verified (Parametric knowledge)

Gemini 3 Pro 72.1%, Gemini 2.5 Pro 54.5%, Claude Sonnet 4.5 29.3%, GPT-5.1 34.9%.

MMMLU (Multilingual Q&A)

Gemini 3 Pro 91.8%, Gemini 2.5 Pro 89.5%, Claude Sonnet 4.5 89.1%, GPT-5.1 91.0%.

Global PIQA (Commonsense reasoning across 100 Languages and Cultures)

Gemini 3 Pro 93.4%, Gemini 2.5 Pro 91.5%, Claude Sonnet 4.5 90.1%, GPT-5.1 90.9%.

MRCR v2 (8-needle) (Long context performance)

128k (average): Gemini 3 Pro 77.0%, Gemini 2.5 Pro 58.0%, Claude Sonnet 4.5 47.1%, GPT-5.1 61.6%.

1M (pointwise): Gemini 3 Pro 26.3%, Gemini 2.5 Pro 16.4%, Claude Sonnet 4.5 (not supported), GPT-5.1 (not supported).

I have not checked every line of this but a loose spot-check looks accurate to me.

That prompt took 1,105 input and 3,901 output tokens, at a cost of 5.6824 cents.

I ran this follow-up prompt:

llm -c 'Convert to JSON'

You can see the full output here, which starts like this:

{
  "metadata": {
    "columns": [
      "Benchmark",
      "Description",
      "Gemini 3 Pro",
      "Gemini 2.5 Pro",
      "Claude Sonnet 4.5",
      "GPT-5.1"
    ]
  },
  "benchmarks": [
    {
      "name": "Humanity's Last Exam",
      "description": "Academic reasoning",
      "sub_results": [
        {
          "condition": "No tools",
          "gemini_3_pro": "37.5%",
          "gemini_2_5_pro": "21.6%",
          "claude_sonnet_4_5": "13.7%",
          "gpt_5_1": "26.5%"
        },
        {
          "condition": "With search and code execution",
          "gemini_3_pro": "45.8%",
          "gemini_2_5_pro": null,
          "claude_sonnet_4_5": null,
          "gpt_5_1": null
        }
      ]
    },

Analyzing a city council meeting

To try it out against an audio file I extracted the 3h33m of audio from the video Half Moon Bay City Council Meeting - November 4, 2025. I used yt-dlp to get that audio:

yt-dlp -x --audio-format m4a 'https://www.youtube.com/watch?v=qgJ7x7R6gy0'

That gave me a 74M m4a file, which I ran through Gemini 3 Pro like this:

llm -m gemini-3-pro-preview -a /tmp/HMBCC\ 11⧸4⧸25\ -\ Half\ Moon\ Bay\ City\ Council\ Meeting\ -\ November\ 4,\ 2025\ \[qgJ7x7R6gy0\].m4a 'Output a Markdown transcript of this meeting. Include speaker names and timestamps. Start with an outline of the key meeting sections, each with a title and summary and timestamp and list of participating names. Note in bold if anyone raised their voices, interrupted each other or had disagreements. Then follow with the full transcript.'

That failed with an "Internal error encountered" message, so I shrunk the file down to a more manageable 38MB using ffmpeg:

ffmpeg -i "/private/tmp/HMB.m4a" -ac 1 -ar 22050 -c:a aac -b:a 24k "/private/tmp/HMB_compressed.m4a"

Then ran it again like this (for some reason I had to use --attachment-type this time):

llm -m gemini-3-pro-preview --attachment-type /tmp/HMB_compressed.m4a 'audio/aac' 'Output a Markdown transcript of this meeting. Include speaker names and timestamps. Start with an outline of the key meeting sections, each with a title and summary and timestamp and list of participating names. Note in bold if anyone raised their voices, interrupted each other or had disagreements. Then follow with the full transcript.'

This time it worked! The full output is here, but it starts like this:

Here is the transcript of the Half Moon Bay City Council meeting.

Meeting Outline

1. Call to Order, Updates, and Public Forum

Summary: Mayor Brownstone calls the meeting to order. City Manager Chidester reports no reportable actions from the closed session. Announcements are made regarding food insecurity volunteers and the Diwali celebration. During the public forum, Councilmember Penrose (speaking as a citizen) warns against autocracy. Citizens speak regarding lease agreements, downtown maintenance, local music events, and homelessness outreach statistics.

Timestamp: 00:00:00 - 00:13:25

Participants: Mayor Brownstone, Matthew Chidester, Irma Acosta, Deborah Penrose, Jennifer Moore, Sandy Vella, Joaquin Jimenez, Anita Rees.

2. Consent Calendar

Summary: The Council approves minutes from previous meetings and a resolution authorizing a licensing agreement for Seahorse Ranch. Councilmember Johnson corrects a pull request regarding abstentions on minutes.

Timestamp: 00:13:25 - 00:15:15

Participants: Mayor Brownstone, Councilmember Johnson, Councilmember Penrose, Vice Mayor Ruddick, Councilmember Nagengast.

3. Ordinance Introduction: Commercial Vitality (Item 9A)

Summary: Staff presents a new ordinance to address neglected and empty commercial storefronts, establishing maintenance and display standards. Councilmembers discuss enforcement mechanisms, window cleanliness standards, and the need for objective guidance documents to avoid subjective enforcement.

Timestamp: 00:15:15 - 00:30:45

Participants: Karen Decker, Councilmember Johnson, Councilmember Nagengast, Vice Mayor Ruddick, Councilmember Penrose.

4. Ordinance Introduction: Building Standards & Electrification (Item 9B)

Summary: Staff introduces updates to the 2025 Building Code. A major change involves repealing the city's all-electric building requirement due to the 9th Circuit Court ruling (California Restaurant Association v. City of Berkeley). Public speaker Mike Ferreira expresses strong frustration and disagreement with "unelected state agencies" forcing the City to change its ordinances.

Timestamp: 00:30:45 - 00:45:00

Participants: Ben Corrales, Keith Weiner, Joaquin Jimenez, Jeremy Levine, Mike Ferreira, Councilmember Penrose, Vice Mayor Ruddick.

5. Housing Element Update & Adoption (Item 9C)

Summary: Staff presents the 5th draft of the Housing Element, noting State HCD requirements to modify ADU allocations and place a measure on the ballot regarding the "Measure D" growth cap. There is significant disagreement from Councilmembers Ruddick and Penrose regarding the State's requirement to hold a ballot measure. Public speakers debate the enforceability of Measure D. Mike Ferreira interrupts the vibe to voice strong distaste for HCD's interference in local law. The Council votes to adopt the element but strikes the language committing to a ballot measure.

Timestamp: 00:45:00 - 01:05:00

Participants: Leslie (Staff), Joaquin Jimenez, Jeremy Levine, Mike Ferreira, Councilmember Penrose, Vice Mayor Ruddick, Councilmember Johnson.

Transcript

Mayor Brownstone [00:00:00] Good evening everybody and welcome to the November 4th Half Moon Bay City Council meeting. As a reminder, we have Spanish interpretation services available in person and on Zoom.

Victor Hernandez (Interpreter) [00:00:35] Thank you, Mr. Mayor, City Council, all city staff, members of the public. [Spanish instructions provided regarding accessing the interpretation channel on Zoom and in the room.] Thank you very much.

Those first two lines of the transcript already illustrate something interesting here: Gemini 3 Pro chose NOT to include the exact text of the Spanish instructions, instead summarizing them as "[Spanish instructions provided regarding accessing the interpretation channel on Zoom and in the room.]".

I haven't spot-checked the entire 3hr33m meeting, but I've confirmed that the timestamps do not line up. The transcript closes like this:

Mayor Brownstone [01:04:00] Meeting adjourned. Have a good evening.

That actually happens at 3h31m5s and the mayor says:

Okay. Well, thanks everybody, members of the public for participating. Thank you for staff. Thank you to fellow council members. This meeting is now adjourned. Have a good evening.

I'm disappointed about the timestamps, since mismatches there make it much harder to jump to the right point and confirm that the summarized transcript is an accurate representation of what was said.

This took 320,087 input tokens and 7,870 output tokens, for a total cost of $1.42.

And a new pelican benchmark

Gemini 3 Pro has a new concept of a "thinking level" which can be set to low or high (and defaults to high). I tried my classic Generate an SVG of a pelican riding a bicycle prompt at both levels.

Here's low - Gemini decided to add a jaunty little hat (with a comment in the SVG that says ):

And here's high. This is genuinely an excellent pelican, and the bicycle frame is at least the correct shape:

Honestly though, my pelican benchmark is beginning to feel a little bit too basic. I decided to upgrade it. Here's v2 of the benchmark, which I plan to use going forward:

Generate an SVG of a California brown pelican riding a bicycle. The bicycle must have spokes and a correctly shaped bicycle frame. The pelican must have its characteristic large pouch, and there should be a clear indication of feathers. The pelican must be clearly pedaling the bicycle. The image should show the full breeding plumage of the California brown pelican.

For reference, here's a photo I took of a California brown pelican recently (sadly without a bicycle):

Here's Gemini 3 Pro's attempt at high thinking level for that new prompt:

And for good measure, here's that same prompt against GPT-5.1 - which produced this dumpy little fellow:

And Claude Sonnet 4.5, which didn't do quite as well:

None of the models seem to have caught on to the crucial detail that the California brown pelican is not, in fact, brown.

Tags: gemini, llm, llm-reasoning, pelican-riding-a-bicycle, llm-pricing, ai, llms, llm-release, google, generative-ai

datasette-demo-for-llm-accountant 0.1a0

2025-11-18T01:27:10+00:00

Release: datasette-demo-for-llm-accountant 0.1a0

Demo app for datasette-llm-accountant

Tags: llm, datasette

datasette-llm-accountant 0.1a0

2025-11-18T01:23:03+00:00

Release: datasette-llm-accountant 0.1a0

LLM accounting for Datasette

Tags: llm, datasette

llm-anthropic 0.22

2025-11-15T20:48:38+00:00

llm-anthropic 0.22

New release of my llm-anthropic plugin:

Support for Claude's new structured outputs feature for Sonnet 4.5 and Opus 4.1. #54

Support for the web search tool using -o web_search 1 - thanks Nick Powell and Ian Langworth. #30

The plugin previously powered LLM schemas using this tool-call based workaround. That code is still used for Anthropic's older models.

I also figured out uv recipes for running the plugin's test suite in an isolated environment, which are now baked into the new Justfile.

Tags: llm, anthropic, claude, generative-ai, projects, ai, llms, uv, python

Introducing GPT-5.1 for developers

2025-11-13T23:59:35+00:00

Introducing GPT-5.1 for developers

OpenAI announced GPT-5.1 yesterday, calling it a smarter, more conversational ChatGPT. Today they've added it to their API.

We actually got four new models today:

There are a lot of details to absorb here.

GPT-5.1 introduces a new reasoning effort called "none" (previous were minimal, low, medium, and high) - and none is the new default.

This makes the model behave like a non-reasoning model for latency-sensitive use cases, with the high intelligence of GPT‑5.1 and added bonus of performant tool-calling. Relative to GPT‑5 with 'minimal' reasoning, GPT‑5.1 with no reasoning is better at parallel tool calling (which itself increases end-to-end task completion speed), coding tasks, following instructions, and using search tools---and supports web search⁠ in our API platform.

When you DO enable thinking you get to benefit from a new feature called "adaptive reasoning":

On straightforward tasks, GPT‑5.1 spends fewer tokens thinking, enabling snappier product experiences and lower token bills. On difficult tasks that require extra thinking, GPT‑5.1 remains persistent, exploring options and checking its work in order to maximize reliability.

Another notable new feature for 5.1 is extended prompt cache retention:

Extended prompt cache retention keeps cached prefixes active for longer, up to a maximum of 24 hours. Extended Prompt Caching works by offloading the key/value tensors to GPU-local storage when memory is full, significantly increasing the storage capacity available for caching.

To enable this set "prompt_cache_retention": "24h" in the API call. Weirdly there's no price increase involved with this at all. I asked about that and OpenAI's Steven Heidel replied:

with 24h prompt caching we move the caches from gpu memory to gpu-local storage. that storage is not free, but we made it free since it moves capacity from a limited resource (GPUs) to a more abundant resource (storage). then we can serve more traffic overall!

The most interesting documentation I've seen so far is in the new 5.1 cookbook, which also includes details of the new shell and apply_patch built-in tools. The apply_patch.py implementation is worth a look, especially if you're interested in the advancing state-of-the-art of file editing tools for LLMs.

I'm still working on integrating the new models into LLM. The Codex models are Responses-API-only.

I got this pelican for GPT-5.1 default (no thinking):

And this one with reasoning effort set to high:

These actually feel like a regression from GPT-5 to me. The bicycles have less spokes!

Tags: november-2025-inflection, llm, openai, pelican-riding-a-bicycle, llm-reasoning, ai, llms, llm-release, gpt-5, generative-ai, gpt-codex

datasette-llm-usage 0.1a2

2025-11-08T01:41:13+00:00

Release: datasette-llm-usage 0.1a2

Track usage of LLM tokens in a SQLite table

Tags: llm, datasette

datasette-enrichments-llm 0.1a2

2025-11-08T01:39:12+00:00

Release: datasette-enrichments-llm 0.1a2

Enrich data by prompting LLMs

Tags: datasette, llm

Kimi K2 Thinking

2025-11-06T23:53:06+00:00

Kimi K2 Thinking

Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July. They've now released the Thinking version, also a trillion parameters (MoE, 32B active) and also under their custom modified (so not quite open source) MIT license.

Starting with Kimi K2, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the same time, K2 Thinking is a native INT4 quantization model with 256k context window, achieving lossless reductions in inference latency and GPU memory usage.

This one is only 594GB on Hugging Face - Kimi K2 was 1.03TB - which I think is due to the new INT4 quantization. This makes the model both cheaper and faster to host.

So far the only people hosting it are Moonshot themselves. I tried it out both via their own API and via the OpenRouter proxy to it, via the llm-moonshot plugin (by NickMystic) and my llm-openrouter plugin respectively.

The buzz around this model so far is very positive. Could this be the first open weight model that's competitive with the latest from OpenAI and Anthropic, especially for long-running agentic tool call sequences?

Moonshot AI's self-reported benchmark scores show K2 Thinking beating the top OpenAI and Anthropic models (GPT-5 and Sonnet 4.5 Thinking) at "Agentic Reasoning" and "Agentic Search" but not quite top for "Coding":

I ran a couple of pelican tests:

llm install llm-moonshot
llm keys set moonshot # paste key
llm -m moonshot/kimi-k2-thinking 'Generate an SVG of a pelican riding a bicycle'

llm install llm-openrouter
llm keys set openrouter # paste key
llm -m openrouter/moonshotai/kimi-k2-thinking \
  'Generate an SVG of a pelican riding a bicycle'

Artificial Analysis said:

Kimi K2 Thinking achieves 93% in 𝜏²-Bench Telecom, an agentic tool use benchmark where the model acts as a customer service agent. This is the highest score we have independently measured. Tool use in long horizon agentic contexts was a strength of Kimi K2 Instruct and it appears this new Thinking variant makes substantial gains

CNBC quoted a source who provided the training price for the model:

The Kimi K2 Thinking model cost $4.6 million to train, according to a source familiar with the matter. [...] CNBC was unable to independently verify the DeepSeek or Kimi figures.

MLX developer Awni Hannun got it working on two 512GB M3 Ultra Mac Studios:

The new 1 Trillion parameter Kimi K2 Thinking model runs well on 2 M3 Ultras in its native format - no loss in quality!

The model was quantization aware trained (qat) at int4.

Here it generated ~3500 tokens at 15 toks/sec using pipeline-parallelism in mlx-lm

Here's the 658GB mlx-community model.

Tags: llm, llm-reasoning, pelican-riding-a-bicycle, ai, ai-in-china, llms, moonshot, llm-release, generative-ai, openrouter, kimi, artificial-analysis, mlx