Which AI model fools people most?

Live ranking from real quiz answers. Genuine photographs are fixed at 1500 — anything above that line gets picked as “the real one” more often than reality does.

Limited to the models built into this quiz — not every model on the market, and not always the latest version of each. A model's absence here says nothing about how good it is.

Image models

19 models listed · 849 AI images in the quiz · click a column to sort

			Confidence
—	Real image	1500	—	1898	1110	58%	—
1	FLUX.2 [klein] 9BBlack Forest Labs	1383	1258–1508	46	11	29%	14
2	Kling Image V3Kuaishou	1314	1196–1432	54	10	19%	10
3	Z-ImageAlibaba	1299	1263–1334	626	113	18%	133
4	Imagen 2Google	1295	1245–1346	494	78	38%	29
5	Gemini 2.5 Flash Image / Nano BananaGoogle	1295	1226–1363	165	30	18%	14
6	Juggernaut Pro FluxRunDiffusion	1291	1232–1349	253	43	19%	33
7	Stable Diffusion 3.5 LargeStability AI	1275	1169–1380	79	12	15%	10
8	Seedream 4.5ByteDance	1273	1227–1319	420	66	16%	33
9	DALL·E 3OpenAI	1263	1172–1354	121	16	13%	27
10	Seedream 4ByteDance	1263	1166–1361	99	14	14%	13
11	SDXL-LightningByteDance	1239	1149–1329	131	16	12%	72
12	Qwen-Image-MaxAlibaba	1239	1104–1374	54	7	13%	12
13	Juggernaut Flux LightningRunDiffusion	1233	1136–1329	112	14	13%	10
14	FLUX.1 [schnell]Black Forest Labs	1233	1192–1273	658	81	12%	157
15	Stable DiffusionStability AI	1228	1149–1307	191	22	15%	37
16	GPT Image 1.5OpenAI	1212	1149–1276	283	32	11%	23
17	FLUX.1 [dev]Black Forest Labs	1189	1123–1255	301	29	10%	41
18	Kling IMAGE 3.0 OmniKuaishou	1169	1085–1252	201	18	9%	24
19	FLUX.2 [max]Black Forest Labs	1103	964–1242	100	6	6%	10

Dimmed rows have fewer than 60 appearances — early evidence, not yet a settled rating.

A model joins this table once it has at least 10 images in the quiz and has appeared in at least 30 answers — below that, the number would say more about one lucky (or unlucky) image than about the model itself. New models and images are added regularly, so more entries — and firmer ratings — are on the way.

In the quiz but not yet listed: FLUX.2 LoRA Gallery: Realism (fal), FLUX1.1 [pro] (Black Forest Labs), Imagen 4 (Google), Lucid Realism (Leonardo AI), Titan Image Generator G1 v1 (Amazon) — fewer than 10 images in the quiz so far; FLUX.2 [pro] (Black Forest Labs), GPT Image 2 Medium (OpenAI), Grok Imagine Image Quality (xAI), Ideogram 4.0 Quality (Ideogram), Imagen 3 Fast (Google), Imagen 4 Ultra (Google), MAI-Image-2.5 (Microsoft AI), Nano Banana 2 Lite (Google), Nano Banana 2 with Web Search (Google), Qwen Image 2.0 Pro (Alibaba), Recraft V3 (Recraft), Reve 2.1 (Reve AI), Seedream 5.0 Pro (ByteDance) — shown too rarely so far, under 30 answers.

Last recomputed 4 Aug 2026, 03:15 · refreshed nightly

Add your own answers

Every round you play feeds straight into these numbers.

Architecture and geometry

Paintings

Brushwork and composition

Cars

Reflections and badges

🎬 Video quizzes

Not in the ranking above yet — too few answers so far to rate video models.

Gravity, fire, liquids

How the rating works

Bradley-Terry, not a win count. Each round counts as a choice among the options actually on screen, so beating strong rivals is worth more than beating weak ones. Two-option rounds and four-option rounds therefore combine without their different odds distorting anything.

Read the range, not the position. Where two intervals overlap, the order between those models is not established. Dimmed rows have fewer than 20 appearances and are listed for completeness only.

Pool size is context. A model represented by three images is judged on those three images, however often they were shown.

Replays don't get extra weight. Only your first look at a round counts — after that you'd recognise it, and it stops being a fresh judgment.

Limits. Only answers from players who accepted analytics are counted, and the method assumes all players judge alike. This measures our image pool, not a model's ceiling.