LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Embed our charts and tables

Claude Opus 5.5
57.6
Claude Sonnet 5.5
56.0
Claude Fable 5.1
53.4

Our charts, on your site · read October 20

our_charts_on_your_site.py


        # Our charts, on your site, read October 20
        leaders = {
            "Claude Opus 5.5": 57.6,    "Claude Sonnet 5.5": 56.0,    "Claude Fable 5.1": 53.4,
        }

Every figure below is licensed CC BY 4.0: put it on any site, commercial ones included, and keep the visible source link. Paste the code as it is: the frame updates itself when our data refreshes, and the link under it names the page the numbers come from.

Cost per solved task against coding index

Our signature chart: each dot is a model with both numbers, the stepped line is the best index you can buy at each cost.

Open the frame on its own

<iframe src="https://llmbenchmark.ai/embed/cost-quality/all" title="Cost per solved task against coding index, LLMBenchmark.ai" width="100%" height="700" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/cost-per-task">LLMBenchmark.ai, cost per solved coding task</a></p>

How many benchmarks stand behind a score

One bar across the whole catalog, split by how many independent coding benchmarks measured each model.

Open the frame on its own

<iframe src="https://llmbenchmark.ai/embed/coverage/catalog" title="How many benchmarks stand behind an LLM score, LLMBenchmark.ai" width="100%" height="240" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/methodology">LLMBenchmark.ai, benchmark coverage of LLMs</a></p>

The ten open-weight models rising fastest on Hugging Face, with downloads and coding index. Refreshes daily.

Open the frame on its own

<iframe src="https://llmbenchmark.ai/embed/trending/open-weights" title="Trending open-weight LLMs on Hugging Face, LLMBenchmark.ai" width="100%" height="520" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/trending">LLMBenchmark.ai, new and trending LLMs</a></p>

New models this month

The latest releases with their price and coding index, newest first. Refreshes daily.

Open the frame on its own

<iframe src="https://llmbenchmark.ai/embed/trending/new" title="New LLMs this month, LLMBenchmark.ai" width="100%" height="520" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/trending">LLMBenchmark.ai, new LLMs</a></p>

Any comparison table

Coding index, the benchmarks behind it, price and cost per solved task for any of the 2145 pairs we compare.

<iframe src="https://llmbenchmark.ai/embed/compare/claude-fable-5-vs-claude-fable-5-1" title="Claude Fable 5 vs Claude Fable 5.1, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-fable-5-vs-claude-fable-5-1">LLMBenchmark.ai, Claude Fable 5 vs Claude Fable 5.1</a></p>

Home page figures

The charts and cards from our home page, each in its own frame. Refreshed daily with the data.

<iframe src="https://llmbenchmark.ai/embed/home/quality-price" title="LLM quality against price, LLMBenchmark.ai" width="100%" height="760" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/leaderboard">LLMBenchmark.ai, LLM quality against price</a></p>

Any "best for" list

The first ten of any of our 75 lists: best for coding, cheapest working answer, open weights, longest context and the rest.

<iframe src="https://llmbenchmark.ai/embed/best/cheapest-working-answer" title="Cheapest LLM per solved coding task, LLMBenchmark.ai" width="100%" height="520" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/best/cheapest-working-answer">LLMBenchmark.ai, Cheapest LLM per solved coding task</a></p>

Any model card

Coding index, every benchmark behind it, price and cost per solved task for any of the 136 ranked models. Good next to a review or a changelog.

<iframe src="https://llmbenchmark.ai/embed/model/claude-opus-5-5" title="Claude Opus 5.5 coding benchmarks and price, LLMBenchmark.ai" width="100%" height="420" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/models/claude-opus-5-5">LLMBenchmark.ai, Claude Opus 5.5 benchmarks and pricing</a></p>

Terms

  1. Licensed CC BY 4.0: free for any site, personal or commercial, with credit to LLMBenchmark.ai. The visible source link under the frame is that credit. No sign-up, no key.
  2. The source link under the frame stays visible, readable and clickable, pointing at the page it names. Removing it, hiding it or covering it ends the permission to embed.
  3. Keep the frame as we serve it. Do not crop out its credit line or restyle the numbers inside it.
  4. The numbers come from the public sources named on each full page, and their own terms apply to that data. For the raw dataset, use the JSON download and cite the refresh date.

Download the dataset as JSON · Methodology