All runs
44 tasks, from summaries to building web pages, then harder ones for larger models. The site grades every answer, and you can read each one.
Run it on a model
From your browser, on a model you run with Ollama, LM Studio, llama.cpp or OpenRouter; or by your coding agent, with one message to paste.
Run the benchmark Tell your agent
Terminal and API: For agents. Curious what the models build? What models built.
Results 21 entries
Ranked by score: speed times the share of points passed, with the harder tasks counting 3. A tie goes to more points, then more tasks passed, then the earlier run. Runs that do not rank come after every ranked run, ordered by points, then tasks passed, then the earlier run, and each says why on its row. Each account, or each machine for runs posted without one, keeps its best run of each model and way of answering; 64 repeat runs not listed.
These runs took resyn-tasks@5, an earlier version of the suite. Its scores are not comparable with resyn-tasks@6. See resyn-tasks@6 results
| Model | Passed | Points | Summarize | Extract | Instructions | Reason | Code | Tools | Pages | Games | Write | Fix | Plan | tok/s | Tokens | By | Date |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8-27B-FastOther · llama-swap · resyn-bench 2 · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 44/44 | 64/64 | 5/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 5/5 | 2/2 | 3/3 | 2/2 | 3/3 | 24.3 | 54k | uwuvia OpenCode | 2026-11-01 |
| Qwen3.8-Flash-Nextllama.cpp · resyn.cloud in the browser · M4 Max 128 GB · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 44/44 | 64/64 | 5/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 5/5 | 2/2 | 3/3 | 2/2 | 3/3 | 27.6 | 127k | uwu | 2026-11-01 |
| OpenAI-gpt-oss-120bOther · llama-swap · resyn-bench 2 · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 43/44 | 63/64 | 4/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 5/5 | 2/2 | 3/3 | 2/2 | 3/3 | 78.8 | 44k | uwuvia OpenCode | 2026-10-31 |
| OpenAI-gpt-oss-20bOther · llama-swap · resyn-bench 2 · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 42/44 | 60/64 | 4/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 5/5 | 2/2 | 3/3 | 2/2 | 2/3 | 109 | 81k | uwuvia OpenCode | 2026-10-31 |
| Qwen3.8-27B-AbliteratedOther · llama-swap · resyn-bench 2 · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 42/44 | 60/64 | 5/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 4/5 | 1/2 | 3/3 | 2/2 | 3/3 | 22.7 | 231k | uwuvia OpenCode | 2026-10-31 |
| Qwen3.8-27B-InstructOther · llama-swap · resyn-bench 2 · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 41/44 | 57/64 | 5/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 4/5 | 0/2 | 3/3 | 2/2 | 3/3 | 23.8 | 78k | uwuvia OpenCode | 2026-11-01 |
| Qwen3.8-27BOther · llama.cpp llama-swap (version not exposed) · resyn-bench 2 · M4 Max 128 GB · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 41/44 | 57/64 | 5/5 | 5/5 | 5/5 | 5/5 | 4/4 | 5/5 | 4/5 | 0/2 | 3/3 | 2/2 | 3/3 | 21.9 | 271k | uwuvia OpenCode | 2026-11-05 |
| Gemma-4-31BOther · llama.cpp llama-swap (version not exposed) · resyn-bench 2 · M4 Max 128 GB · 1 run of this modelNot ranked: it was posted under an earlier version of the task suite. | 27/44 | 43/64 | — | — | — | 5/5 | 4/4 | 5/5 | 5/5 | 1/2 | 2/3 | 2/2 | 3/3 | 9.8 | 318k | uwuvia OpenCode | 2026-11-04 |
| Qwen3.5-4BOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 23/44 | 23/64 | 4/5 | 4/5 | 5/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 62.7 | 52k | uwuvia OpenCode | 2026-10-31 |
| Qwen3-4B-Instruct-AbliteratedOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 22/44 | 22/64 | 4/5 | 4/5 | 4/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 89.8 | 9.9k | uwuvia OpenCode | 2026-10-31 |
| Qwen3-4B-Instruct-Abliterated-TransformOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 22/44 | 22/64 | 4/5 | 4/5 | 4/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 87.3 | 10k | uwuvia OpenCode | 2026-10-31 |
| Qwen3-8BOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 22/44 | 22/64 | 3/5 | 4/5 | 5/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 53 | 28k | uwuvia OpenCode | 2026-10-31 |
| Qwen3-8B-AbliteratedOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 22/44 | 22/64 | 3/5 | 4/5 | 5/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 53 | 25k | uwuvia OpenCode | 2026-10-31 |
| Satyr-V0.1-4BOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 22/44 | 22/64 | 5/5 | 4/5 | 4/5 | — | 1/4 | 5/5 | 3/5 | — | — | — | — | 55.3 | 26k | uwuvia OpenCode | 2026-10-31 |
| Qwen3-8B-TransformOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 21/44 | 21/64 | 3/5 | 4/5 | 4/5 | — | 1/4 | 5/5 | 4/5 | — | — | — | — | 52.5 | 8.7k | uwuvia OpenCode | 2026-10-31 |
| Qwen3.5-4B-InstructOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 20/44 | 20/64 | 3/5 | 4/5 | 4/5 | — | 1/4 | 4/5 | 4/5 | — | — | — | — | 64.3 | 13k | uwuvia OpenCode | 2026-10-31 |
| Llama3.2-3B-Instruct-TransformOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 15/44 | 15/64 | 4/5 | 3/5 | 4/5 | — | 1/4 | 0/5 | 3/5 | — | — | — | — | 67 | 12k | uwuvia OpenCode | 2026-10-31 |
| Hermes-3-Llama-3.2Other · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 13/44 | 13/64 | 2/5 | 3/5 | 3/5 | — | 0/4 | 1/5 | 4/5 | — | — | — | — | 109 | 4.9k | uwuvia OpenCode | 2026-10-31 |
| Qwen3.5-0.8B-AutocompleteOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 13/44 | 13/64 | 1/5 | 3/5 | 3/5 | — | 1/4 | 5/5 | 0/5 | — | — | — | — | 308 | 33k | uwuvia OpenCode | 2026-10-31 |
| Llama-3.2-3B-UncensoredOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 9/44 | 9/64 | 2/5 | 3/5 | 2/5 | — | 0/4 | 0/5 | 2/5 | — | — | — | — | 67 | 9.5k | uwuvia OpenCode | 2026-10-31 |
| Qwen2-VL-7B-InstructOther · Ollama v262 · resyn-bench 2Not ranked: it was posted under an earlier version of the task suite. | 8/44 | 8/64 | 0/5 | 2/5 | 2/5 | — | 0/4 | 1/5 | 3/5 | — | — | — | — | 59.7 | 5k | uwuvia OpenCode | 2026-10-31 |
Scrolls sideways to show every column.
The tasks
Every task passes or fails on checks the site runs. Pages are checked for what was asked, then shown as the model built them.
Summarizing 5 tasks
- One-sentence summary. Summarize this in one sentence of at most 30 words.
- Meeting notes in three bullets. Summarize these meeting notes as exactly three bullet points, each at most 20 words. Keep only the decisions and ownership changes that matter. Output only the bullet points.
- Review sentiment and complaint. Read this product review and answer in exactly this format: Sentiment: <positive, negative or mixed> Complaint: <the main complaint in a few words>
- Faithful summary of a study. Summarize this in at most 50 words. Keep the key numbers. Do not add anything the text does not say.
- Action items from an email thread. List every action item in this email thread that someone has committed to do, as lines of the form "- <owner>: <action>". Leave out offers that were declined and things that turned out not to be needed. Output only the list.
Extracting 5 tasks
- Fields from an email as JSON. Extract these fields from the email as a JSON object with exactly these keys: "name" (the sender's full name), "company", "meeting_date" (YYYY-MM-DD) and "attendees" (a number). Output only the JSON.
- Every email address, once. List every email address written out in full in this text (like name@example.com), one per line, in the order they first appear, without duplicates. Leave out any inbox the text says is closed. Output only the addresses.
- A list as CSV. Convert this shopping list to CSV with the header row item,qty,price. Write prices as plain numbers without a currency sign. Output only the CSV.
- The real deadline. What is the final submission deadline? Answer with the date only, in YYYY-MM-DD format.
- Warnings and errors from a log. From this log, return a JSON array with one object per WARN or ERROR line, in order, each with the keys "time" (HH:MM:SS), "level" and "message". Output only the JSON.
Following instructions 5 tasks
- Exactly one word. Reply with exactly the word OK and nothing else.
- Three lowercase lines. Write exactly three lines about the sea. Every line must be entirely lowercase, and the third line must end with a question mark. Output only the three lines.
- Exact JSON shape. Return a JSON object with exactly two keys: "colors", a list of exactly three color names in lowercase, and "count", the number 3. Output only the JSON.
- Sort a list. Sort these words alphabetically, ignoring case, and output them on one line separated by commas: pear, Apple, banana, cherry, apricot
- A name with three rules. Suggest a product name for a solar-powered lamp. Rules: exactly two words, both capitalized, and the letter "e" must not appear anywhere. Output only the name.
Reasoning 5 tasks
- Unit price. A shop sells pencils at 4 for $1.00. How much do 7 pencils cost, in dollars? Work it out, then end with a line "ANSWER: <number>".
- Days of the week. Today is Sunday. What day of the week will it be 128 days from today? Work it out, then end with a line "ANSWER: <day>".
- Who owns the cat. Gus, Dee and Hal each own exactly one pet: a cat, a dog or a fish, all different. Hal does not own the dog. Gus owns the fish. Who owns the cat? Work it out, then end with a line "ANSWER: <name>".
- Arrival time. A train leaves at 13:35 and the trip takes 2 hours 25 minutes. At what time does it arrive? Work it out, then end with a line "ANSWER: <HH:MM>" in 24-hour time.
- Filling a tank. A tank holds 120 liters. Pipe A alone fills it in 3 hours, pipe B alone fills it in 15 hours, and a drain alone empties a full tank in 3 hours. With all three open and the tank starting empty, how many hours until it is full? Work it out, then end with a line "ANSWER: <number>".
Reading code 4 tasks
- What does it print. What does this Python program print? Work it out, then end with a line "ANSWER: <output>".
- Trace a loop. What does this Python program print? Work it out, then end with a line "ANSWER: <output>".
- Find the bug. This function should return the mean of a non-empty list. Which line has the bug? Work it out, then end with a line "ANSWER: <line number>".
- Run a query in your head. What rows does this SQL query return? Output only the rows, one per line, as customer,total in the query's order.
Using tools 5 tasks
- Call one tool. What's the weather in Lisbon right now, in celsius?
- Don't call a tool when none is needed. What is 12 times 12?
- Two calls for two answers. Convert 250 EUR to USD and to JPY.
- Chain two tools. What is the status of each order for the customer with the email kim@example.com?
- Handle a failed call honestly. Book a table for 2 people at Luigi's tonight at 19:00.
Building pages 5 tasks
- A small website. Build a one-page website for a bakery called "Crumb & Co". It must have a <header> containing an <h1> with the bakery's name; a <nav> with exactly 3 links; a <main> with a <section id="menu"> listing at least 4 items in a list; and a <footer> with the opening hours. Output one complete HTML document and nothing else. Put all CSS and JavaScript inline. Do not load anything from another site: no external scripts, stylesheets, fonts or images.
- A pricing table with a toggle. Build a pricing page with three plans. Each plan is an element with class "plan" containing an element with class "price". Add a <button id="billing-toggle"> that switches every price between monthly and yearly billing when clicked. Output one complete HTML document and nothing else. Put all CSS and JavaScript inline. Do not load anything from another site: no external scripts, stylesheets, fonts or images.
- An accessible sign-up form. Build a sign-up form: <form id="signup"> with inputs id="name", id="email" (type email) and id="password" (type password, minlength at least 8), each with a <label for>, and a submit button. When the form is submitted and valid, prevent the real submission and show a confirmation in an element with id="status" and role="status". Output one complete HTML document and nothing else. Put all CSS and JavaScript inline. Do not load anything from another site: no external scripts, stylesheets, fonts or images.
- A to-do app that remembers. Build a to-do list app with an <input id="new-task">, a <button id="add"> and a <ul id="tasks">. Clicking add appends the text as an <li> with its own remove button. Save the list in localStorage under the key "todos" and load it again when the page opens. Output one complete HTML document and nothing else. Put all CSS and JavaScript inline. Do not load anything from another site: no external scripts, stylesheets, fonts or images.
- A bar chart in SVG. Draw an inline SVG bar chart of coffee sold: Mon 12, Tue 30, Wed 18, Thu 24, Fri 6. Each bar is a <rect class="bar"> whose height attribute is proportional to its value, each bar is labelled with its day in a <text>, and the <svg> has a <title> or an aria-label. Write the bars and labels directly in the SVG markup, not with JavaScript. Output one complete HTML document and nothing else. Put all CSS and JavaScript inline. Do not load anything from another site: no external scripts, stylesheets, fonts or images.
Building games 2 tasks
- Build 2048. Build the game 2048 as one web page, playable with the arrow keys, with the board drawn on the page.
- Build Snake. Build Snake as one web page on a 10 by 10 grid, playable with the arrow keys (one key press, one step), with the grid drawn on the page.
Writing code 3 tasks
- Merge intervals. Write a JavaScript function mergeIntervals(intervals). intervals is an array of [start, end] pairs of integers with start <= end, in any order, possibly empty. Return a new array of the merged intervals sorted by start: intervals that overlap or touch (one ends where the next starts) become one. Do not change the input array or its pairs.
- An LRU cache. Write a JavaScript class LRUCache: a least-recently-used cache of integer keys and values.
- Evaluate arithmetic. Write a JavaScript function evaluate(expr) that returns the value of an arithmetic expression given as a string. The expression has non-negative integers, the operators + - * /, parentheses, unary minus (as in -3, - -3, 2 * -3 or -(1 + 2)) and spaces anywhere between tokens. * and / bind tighter than + and -, and operators of the same kind group from the left. / is integer division that truncates toward zero: 7 / 2 is 3 and -7 / 2 is -3. Dividing by zero must throw an Error. Do not use eval or Function.
Fixing code 2 tasks
- Fix the bookings module. This JavaScript module has one bug. The occupancy report sometimes counts one booked night more than there is in the range it was asked about.
- Fix the CSV reader. This JavaScript module has one bug. A doubled quote inside a quoted field, as in "say ""hi""", does not come out as one double quote.
Planning and data 3 tasks
- A query over hidden data. Write one SQLite query that answers the question below. The site runs it on its own copy of these tables, filled with rows you have not seen.
- Schedule five meetings. Five people each have one meeting today: Cleo, Dev, Fay, Gus, Noa. The five meetings are at different times, 09:00, 10:00, 11:00, 13:00, 14:00 (in that order: 10:00 is right after 09:00, 13:00 right after 11:00), and in different rooms. The list of rooms, in order: Birch, Cedar, Elm, Pine, Rowan.
- A replacement in ten calls or fewer. Hi, it's ana.silva@example.com. My kettle arrived with a cracked lid. Can you sort it out?