Playground · Claude Haiku 5.5 model page
Claude Haiku 5.5 in the playground
18 tests; our pick in 0. Each answer is linked to the test, where it runs live beside the other models'.
- Our pick
- 0 of 18 tests
- Checks passed
- 85% 58 of 68
- All checks passed
- 10 of 18 tests
- Rank
- 8 of 11 models by checks passed
- Cost
- $0.11 every try; $0.11 for the answers shown
- Time
- 16 min every try; 16 min for the answers shown
- Tries
- 18 for 18 answers
- Thinking
- 50% of its output tokens
| Test | Our notes | Checks | Time | Cost | Thinking |
|---|---|---|---|---|---|
| A map of the world from memory Drawing · 11 models |
A plain equirectangular map in beige and blue, with Scandinavia, Britain, Italy, Hudson Bay, Japan, the Philippines, New Guinea and New Zealand. Africa is broken: its northern coast was written with southern latitudes, so the continent starts just above the Equator and the Horn folds down to Madagascar, leaving open sea where the Sahara should be. The Black Sea is a rectangle, the Pacific labels are centred on the left edge so they read "ific Ocean", and "North Atlantic" runs onto Africa's corner. | 2.5 of 4 | 76 s | $0.010 | 72% |
| Draw a unicorn Drawing · 11 models |
A white cartoon unicorn on a green patch, with a gold horn, a purple-to-blue gradient mane and tail, pink hooves and a blushing cheek. All four legs, mane and tail are in place, but the neck is a hard-cornered slab whose outline runs across the body, the mane strands hang down the front of the neck, and the horn's spiral ticks stick out past its edge. The fastest answer, at 16 seconds. | 2.5 of 3 | 16 s | $0.002 | 37% |
| The Starry Night, redrawn in SVG Drawing · 11 models |
A soft, cartoon-like version: rough-edged blue sweeps and separate hook-shaped curls across the sky, five-pointed stars in soft glows and a tall dark cypress cone on the left. Hills and a village of six lit cottages sit below, with a church whose spire is a thin wavy line. The moon is meant to be a crescent, but its mask is centred on the disc, so it shows as a thin bright ring in a glow. There is no great swirl, and at about 130 shapes (10 KB) it reads as an illustration rather than a painting. | 2.5 of 4 | 43 s | $0.005 | 39% |
| Ball bouncing in a spinning hexagon Simulation · 11 models |
A blue hexagon spinning at 1 rad/s beside a slider panel for gravity, bounciness, friction, drag and spin (including reverse), with a ball that changes colour with speed, a spin marker, a trail, click-to-drop and pause. Bounces lose height and turn into hops and rolls along the lower walls; in our 20-second log the ball never sank into a wall or left, and impacts nudge the hexagon's spin between 0.94 and 1.04 rad/s. The panel covers the hexagon's left corner as it turns. It took 97 seconds. | 3 of 3 | 97 s | $0.012 | 69% |
| The solar system, to scale in time Animation · 11 models |
A dark canvas with all nine bodies labelled, real periods in the code, slower, pause and faster buttons, a speed slider from minutes to ten years per second, a labels toggle and reset. Speeds are right (Mercury about 4.2 laps per Earth year in our tracking) and each button steps the speed as labelled. But Neptune starts at the bottom of its orbit, under the control bar, in both a 1000 by 700 and a 1440 by 900 window, and at the default 1 day per second it stays hidden for hours; the Sun's label also overlaps Mars and Venus at the start. The fastest answer, at 38 seconds. | 3 of 3 | 38 s | $0.005 | 26% |
| A product page from one feed row Business · 11 models |
A plain, tidy page with three flat, boot-like socks side by side, colour chips under "One pair of each colour" and a details list with weight, product code and GTIN. Every line traces back to the feed. Adding with no size gives "Please choose a size before adding to your basket."; with a size it shows "Added to basket: Merino crew socks, 3 pack, size M." and the basket count goes up. The fastest answer, at 28 seconds. | 5 of 5 | 28 s | $0.003 | 24% |
| A pricing table with a monthly/yearly switch Web page · 11 models |
A light page with a toggle switch, a "Save on yearly" tag and a "Most popular" Team card with a purple border. The switch, and the Monthly and Yearly words beside it, move the prices to £5 and £9 "Billed yearly" and back, and the four FAQ answers, in rows that open and close, repeat only the brief. Plain and correct, and the fastest and cheapest answer at 19 seconds and $0.003. | 4 of 4 | 19 s | $0.003 | 16% |
| Pelican riding a bicycle Drawing · 11 models |
A simple flat drawing: a white oval bird with a purple scarf and a long orange beak and pouch, on a red bicycle under a yellow sun. It sits on the saddle with one leg reaching down, but the foot rests on the frame beside a bare crank with no pedal, the wing is folded on its back and the head is far from the handlebars. The fastest and cheapest answer, at 13 seconds and $0.001. | 2 of 3 | 13 s | $0.001 | 33% |
| Newton's cradle Simulation · 11 models |
A dark wooden frame with five steel balls, an elasticity slider (0.97) and a reset button. The ball follows the mouse on its string, but the collisions are broken: neighbours push each other apart at any distance, so pulling out the end ball shoves the other four away as a block, and on release it never reaches the row. The two groups rock to and fro with a wide gap between them and are still moving after 100 seconds. The cheapest answer, at $0.011. | 1 of 3 | 100 s | $0.011 | 72% |
| A newsletter email that works in email Business · 11 models |
A dark green "October letter" header, a flat Moss swatch, four numbered washing habits and AUTUMN15 in a dashed box, all in tables with inline styles. Dark mode is handled and the code stays clear, though the step numbers fade almost to nothing. It leaves the address as a placeholder but invents product facts ("Spun from 100% merino", "Mid-weight · Crew", "UK sizes 4 to 13", "made in small batches in the UK") and calls the offer "15% off everything". The cheapest and fastest answer, at $0.004 in 29 seconds. | 4 of 5 | 29 s | $0.004 | 12% |
| A landing page for a photo-book app Web page · 11 models |
A calm cream-and-teal page ("Your camera roll, finally on paper.") with a CSS hardback and polaroids, four steps, gradient sample spreads and a "Make my book for £19" button. It repeats the offer throughout and invents no reviews, ratings, customer counts or extra prices; it does add that delivery is included and the paper is heavy and matte, and its reply lists what it made up. The header's "Make my book" button is brown on dark teal and can't be read, and on a phone the polaroid captions spill over their photos. The cheapest and fastest answer, at $0.008 in 64 seconds. | 2.5 of 3 | 64 s | $0.008 | 10% |
| The jelly effect: frontier models, one prompt Animation · 11 models |
A glossy pink ball on a pale lilac page, with a hint line and a double-tap that changes its colour (aqua next). A click swells it by a few pixels for a fraction of a second, and dragging slides the whole ball after the pointer while it stays perfectly round; on release it drifts back to the centre over more than three seconds. The cheapest answer on the page ($0.014, 130 seconds), but a ball rather than a jelly. | 1 of 3 | 2.2 min | $0.014 | 72% |
| Conway's Game of Life Simulation · 11 models |
A dark 80 by 50 board that opens with a glider, with play, step, clear, a speed slider in generations per second, live generation and population counts, and buttons for the three asked-for patterns. Every test passed: the blinker flips, the drawn glider moves one cell diagonally in four steps, the pulsar repeats every three, and the gun had fired three gliders after 120 generations. The board does not shrink to fit, so it scrolls in a narrow window. The cheapest answer, at $0.0045 in 35 seconds. | 4 of 4 | 35 s | $0.005 | 28% |
| Flappy Bird in one file Game · 11 models |
A faithful classic with a yellow bird, green pipes, drifting clouds and a striped ground under a "FLAPPY BIRD" title. Flapping and gravity feel right; we passed 12 pipes, and a crash brings up a Game Over card with score and best. A short pause stops an accidental restart, then a tap or Space starts a new run at 0 with a flap. The clouds have odd sharp spikes on their edges. The cheapest answer, at $0.0065. | 4 of 4 | 55 s | $0.006 | 47% |
| Chess with every rule Game · 11 models |
A brown wooden board with a dark side panel, a move list in standard notation ("4. Qxf7#") and resign and new-game buttons, but no undo or flip. All four sequences played correctly, and so did our probes: Black could not ignore Qh5+, promotion offers a choice of four pieces, and the ten-move stalemate ends with "Stalemate! The game is a draw." The status reads "White to move", adds "(in check!)" when needed, and shows "Checkmate! White wins." at the end. The cheapest answer, at about a cent. | 5 of 5 | 91 s | $0.011 | 59% |
| A category page from a product feed Business · 11 models |
A plain "Rain jackets" page with checkbox filters for brand, colour (with swatches) and size, min and max price boxes, a reset button and five sorts. Every filter, combination and sort we ran returned exactly the right jackets, and an impossible pairing shows "0 of 12 products". Its only addition is a header line ("Waterproof shells, parkas and rain gear for every season"), with no claims on the products. The trench gets a belt and the cape its own shape, but the other jackets share one short-sleeved outline. The cheapest answer, at $0.0056. | 4 of 4 | 46 s | $0.006 | 32% |
| An animated SVG logo Drawing · 11 models |
An orange-and-navy swept wing slides in from the left over three orange speed lines, then "KESTREL" draws itself letter by letter in a rounded monoline, and an orange swoosh underlines it at about 2.4 seconds. There is no card or tagline. The name is clear, but the mark is a lone wing with no head or body, so it reads more as a fin than a bird, and each letter shows as a small dot before it draws on. The cheapest answer, at $0.0026. | 4 of 4 | 27 s | $0.003 | 58% |
| An analogue clock that tells the time Drawing · 11 models |
A navy dial with cream Roman numerals, gold baton markers, a gold bezel, sword-shaped hands and a red second hand, with a digital readout and the date underneath. The time matched the real clock to the second, and at 10:42 the hour hand sits about two thirds of the way from X to XI. The hour markers touch the edges of VIII and IV, but every numeral is readable. The cheapest answer on the page, at $0.0034. | 4 of 4 | 30 s | $0.003 | 27% |
Time and cost are for the answer shown; when it took more than one try, the second line counts every try, and sorting uses every try. Thinking is the share of the answer's output tokens spent reasoning before it wrote.
Tries
Every answer came on the first try
Against the other models
Checks passed on each test
Claude Haiku 5.5's column is marked.
| Test | Claude Opus 5.5 | GPT-6.1 Sol | Kimi K3 | Claude Fable 5.1 | Muse Spark 1.3 | DeepSeek V4.1 Flash | Mistral Large 4 | Claude Haiku 5.5 | Grok 4.7 | Qwen3.8 Max (0902) | Gemini 3.8 Flash |
|---|---|---|---|---|---|---|---|---|---|---|---|
| A map of the world from memory | 4/4★Claude Opus 5.5: 4 of 4 checks, our pick | 3.5/4GPT-6.1 Sol: 3.5 of 4 checks | 4/4Kimi K3: 4 of 4 checks | 4/4Claude Fable 5.1: 4 of 4 checks | 3/4Muse Spark 1.3: 3 of 4 checks | 2/4DeepSeek V4.1 Flash: 2 of 4 checks | 3/4Mistral Large 4: 3 of 4 checks | 2.5/4Claude Haiku 5.5: 2.5 of 4 checks | 3.5/4Grok 4.7: 3.5 of 4 checks | 0.5/4Qwen3.8 Max (0902): 0.5 of 4 checks | 3/4Gemini 3.8 Flash: 3 of 4 checks |
| Draw a unicorn | 2.5/3Claude Opus 5.5: 2.5 of 3 checks | 3/3★GPT-6.1 Sol: 3 of 3 checks, our pick | 2.5/3Kimi K3: 2.5 of 3 checks | 2.5/3Claude Fable 5.1: 2.5 of 3 checks | 1.5/3Muse Spark 1.3: 1.5 of 3 checks | 1.5/3DeepSeek V4.1 Flash: 1.5 of 3 checks | 2/3Mistral Large 4: 2 of 3 checks | 2.5/3Claude Haiku 5.5: 2.5 of 3 checks | 2/3Grok 4.7: 2 of 3 checks | 2.5/3Qwen3.8 Max (0902): 2.5 of 3 checks | 1.5/3Gemini 3.8 Flash: 1.5 of 3 checks |
| The Starry Night, redrawn in SVG | 4/4Claude Opus 5.5: 4 of 4 checks | 4/4★GPT-6.1 Sol: 4 of 4 checks, our pick | 4/4Kimi K3: 4 of 4 checks | 4/4Claude Fable 5.1: 4 of 4 checks | 2.5/4Muse Spark 1.3: 2.5 of 4 checks | 1.5/4DeepSeek V4.1 Flash: 1.5 of 4 checks | 2.5/4Mistral Large 4: 2.5 of 4 checks | 2.5/4Claude Haiku 5.5: 2.5 of 4 checks | 1.5/4Grok 4.7: 1.5 of 4 checks | 2.5/4Qwen3.8 Max (0902): 2.5 of 4 checks | 3/4Gemini 3.8 Flash: 3 of 4 checks |
| Ball bouncing in a spinning hexagon | 3/3★Claude Opus 5.5: 3 of 3 checks, our pick | 3/3GPT-6.1 Sol: 3 of 3 checks | 3/3Kimi K3: 3 of 3 checks | 3/3Claude Fable 5.1: 3 of 3 checks | 3/3Muse Spark 1.3: 3 of 3 checks | 3/3DeepSeek V4.1 Flash: 3 of 3 checks | 3/3Mistral Large 4: 3 of 3 checks | 3/3Claude Haiku 5.5: 3 of 3 checks | 3/3Grok 4.7: 3 of 3 checks | 3/3Qwen3.8 Max (0902): 3 of 3 checks | 2.5/3Gemini 3.8 Flash: 2.5 of 3 checks |
| The solar system, to scale in time | 3/3★Claude Opus 5.5: 3 of 3 checks, our pick | 3/3GPT-6.1 Sol: 3 of 3 checks | 3/3Kimi K3: 3 of 3 checks | 3/3Claude Fable 5.1: 3 of 3 checks | 3/3Muse Spark 1.3: 3 of 3 checks | 3/3DeepSeek V4.1 Flash: 3 of 3 checks | 3/3Mistral Large 4: 3 of 3 checks | 3/3Claude Haiku 5.5: 3 of 3 checks | 3/3Grok 4.7: 3 of 3 checks | 3/3Qwen3.8 Max (0902): 3 of 3 checks | 3/3Gemini 3.8 Flash: 3 of 3 checks |
| A product page from one feed row | 5/5★Claude Opus 5.5: 5 of 5 checks, our pick | 5/5GPT-6.1 Sol: 5 of 5 checks | 5/5Kimi K3: 5 of 5 checks | 5/5Claude Fable 5.1: 5 of 5 checks | 5/5Muse Spark 1.3: 5 of 5 checks | 5/5DeepSeek V4.1 Flash: 5 of 5 checks | 4/5Mistral Large 4: 4 of 5 checks | 5/5Claude Haiku 5.5: 5 of 5 checks | 4.5/5Grok 4.7: 4.5 of 5 checks | 5/5Qwen3.8 Max (0902): 5 of 5 checks | 5/5Gemini 3.8 Flash: 5 of 5 checks |
| A pricing table with a monthly/yearly switch | 4/4Claude Opus 5.5: 4 of 4 checks | 4/4GPT-6.1 Sol: 4 of 4 checks | 4/4★Kimi K3: 4 of 4 checks, our pick | 4/4Claude Fable 5.1: 4 of 4 checks | 4/4Muse Spark 1.3: 4 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 3.5/4Mistral Large 4: 3.5 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 4/4Grok 4.7: 4 of 4 checks | 3/4Qwen3.8 Max (0902): 3 of 4 checks | 4/4Gemini 3.8 Flash: 4 of 4 checks |
| Pelican riding a bicycle | 3/3Claude Opus 5.5: 3 of 3 checks | 3/3★GPT-6.1 Sol: 3 of 3 checks, our pick | 3/3Kimi K3: 3 of 3 checks | 3/3Claude Fable 5.1: 3 of 3 checks | 3/3Muse Spark 1.3: 3 of 3 checks | 2/3DeepSeek V4.1 Flash: 2 of 3 checks | 3/3Mistral Large 4: 3 of 3 checks | 2/3Claude Haiku 5.5: 2 of 3 checks | 2/3Grok 4.7: 2 of 3 checks | 3/3Qwen3.8 Max (0902): 3 of 3 checks | 2.5/3Gemini 3.8 Flash: 2.5 of 3 checks |
| Newton's cradle | 3/3★Claude Opus 5.5: 3 of 3 checks, our pick | 2.5/3GPT-6.1 Sol: 2.5 of 3 checks | 3/3Kimi K3: 3 of 3 checks | 3/3Claude Fable 5.1: 3 of 3 checks | 3/3Muse Spark 1.3: 3 of 3 checks | 3/3DeepSeek V4.1 Flash: 3 of 3 checks | 2.5/3Mistral Large 4: 2.5 of 3 checks | 1/3Claude Haiku 5.5: 1 of 3 checks | 3/3Grok 4.7: 3 of 3 checks | 3/3Qwen3.8 Max (0902): 3 of 3 checks | 3/3Gemini 3.8 Flash: 3 of 3 checks |
| A newsletter email that works in email | 4.5/5Claude Opus 5.5: 4.5 of 5 checks | 4.5/5★GPT-6.1 Sol: 4.5 of 5 checks, our pick | 4/5Kimi K3: 4 of 5 checks | 4/5Claude Fable 5.1: 4 of 5 checks | 3.5/5Muse Spark 1.3: 3.5 of 5 checks | 4/5DeepSeek V4.1 Flash: 4 of 5 checks | 4/5Mistral Large 4: 4 of 5 checks | 4/5Claude Haiku 5.5: 4 of 5 checks | 4/5Grok 4.7: 4 of 5 checks | 3.5/5Qwen3.8 Max (0902): 3.5 of 5 checks | 3.5/5Gemini 3.8 Flash: 3.5 of 5 checks |
| A landing page for a photo-book app | 2.5/3Claude Opus 5.5: 2.5 of 3 checks | 2.5/3GPT-6.1 Sol: 2.5 of 3 checks | 3/3Kimi K3: 3 of 3 checks | 2/3Claude Fable 5.1: 2 of 3 checks | 2/3Muse Spark 1.3: 2 of 3 checks | 2/3DeepSeek V4.1 Flash: 2 of 3 checks | 3/3Mistral Large 4: 3 of 3 checks | 2.5/3Claude Haiku 5.5: 2.5 of 3 checks | 3/3★Grok 4.7: 3 of 3 checks, our pick | 2/3Qwen3.8 Max (0902): 2 of 3 checks | 3/3Gemini 3.8 Flash: 3 of 3 checks |
| The jelly effect | 3/3★Claude Opus 5.5: 3 of 3 checks, our pick | 3/3GPT-6.1 Sol: 3 of 3 checks | 2.5/3Kimi K3: 2.5 of 3 checks | 3/3Claude Fable 5.1: 3 of 3 checks | 2/3Muse Spark 1.3: 2 of 3 checks | 2.5/3DeepSeek V4.1 Flash: 2.5 of 3 checks | 3/3Mistral Large 4: 3 of 3 checks | 1/3Claude Haiku 5.5: 1 of 3 checks | 3/3Grok 4.7: 3 of 3 checks | 3/3Qwen3.8 Max (0902): 3 of 3 checks | 1/3Gemini 3.8 Flash: 1 of 3 checks |
| Conway's Game of Life | 4/4★Claude Opus 5.5: 4 of 4 checks, our pick | 4/4GPT-6.1 Sol: 4 of 4 checks | 4/4Kimi K3: 4 of 4 checks | 4/4Claude Fable 5.1: 4 of 4 checks | 3.5/4Muse Spark 1.3: 3.5 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 3/4Mistral Large 4: 3 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 4/4Grok 4.7: 4 of 4 checks | 3.5/4Qwen3.8 Max (0902): 3.5 of 4 checks | 4/4Gemini 3.8 Flash: 4 of 4 checks |
| Flappy Bird in one file | 4/4Claude Opus 5.5: 4 of 4 checks | 4/4★GPT-6.1 Sol: 4 of 4 checks, our pick | 4/4Kimi K3: 4 of 4 checks | 4/4Claude Fable 5.1: 4 of 4 checks | 4/4Muse Spark 1.3: 4 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 4/4Mistral Large 4: 4 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 4/4Grok 4.7: 4 of 4 checks | 4/4Qwen3.8 Max (0902): 4 of 4 checks | 4/4Gemini 3.8 Flash: 4 of 4 checks |
| Chess with every rule | 5/5Claude Opus 5.5: 5 of 5 checks | 5/5★GPT-6.1 Sol: 5 of 5 checks, our pick | 5/5Kimi K3: 5 of 5 checks | 5/5Claude Fable 5.1: 5 of 5 checks | 5/5Muse Spark 1.3: 5 of 5 checks | 5/5DeepSeek V4.1 Flash: 5 of 5 checks | 5/5Mistral Large 4: 5 of 5 checks | 5/5Claude Haiku 5.5: 5 of 5 checks | 5/5Grok 4.7: 5 of 5 checks | 5/5Qwen3.8 Max (0902): 5 of 5 checks | 0/5Gemini 3.8 Flash: 0 of 5 checks |
| A category page from a product feed | 4/4★Claude Opus 5.5: 4 of 4 checks, our pick | 4/4GPT-6.1 Sol: 4 of 4 checks | 3.5/4Kimi K3: 3.5 of 4 checks | 3.5/4Claude Fable 5.1: 3.5 of 4 checks | 3/4Muse Spark 1.3: 3 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 3/4Mistral Large 4: 3 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 0/4Grok 4.7: 0 of 4 checks | 3/4Qwen3.8 Max (0902): 3 of 4 checks | 3/4Gemini 3.8 Flash: 3 of 4 checks |
| An animated SVG logo | 4/4Claude Opus 5.5: 4 of 4 checks | 4/4GPT-6.1 Sol: 4 of 4 checks | 4/4Kimi K3: 4 of 4 checks | 4/4★Claude Fable 5.1: 4 of 4 checks, our pick | 4/4Muse Spark 1.3: 4 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 4/4Mistral Large 4: 4 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 4/4Grok 4.7: 4 of 4 checks | 4/4Qwen3.8 Max (0902): 4 of 4 checks | 3.5/4Gemini 3.8 Flash: 3.5 of 4 checks |
| An analogue clock that tells the time | 4/4Claude Opus 5.5: 4 of 4 checks | 4/4★GPT-6.1 Sol: 4 of 4 checks, our pick | 4/4Kimi K3: 4 of 4 checks | 4/4Claude Fable 5.1: 4 of 4 checks | 4/4Muse Spark 1.3: 4 of 4 checks | 4/4DeepSeek V4.1 Flash: 4 of 4 checks | 3/4Mistral Large 4: 3 of 4 checks | 4/4Claude Haiku 5.5: 4 of 4 checks | 3.5/4Grok 4.7: 3.5 of 4 checks | 3.5/4Qwen3.8 Max (0902): 3.5 of 4 checks | 3.5/4Gemini 3.8 Flash: 3.5 of 4 checks |