Skip to content
CreatePricing

Image models for fantasy and tabletop work

Last vote 31 Oct 2026611 counted blind votes16 ranked · 74 in evaluationMethodologyDownload data (CSV)How to cite

74 of 90 models still need votes to be ranked.

Checking your account…

Standings · Overall

Pick a model to see each task. Sorted by score · ranges are 95%
Overall ranking of 16 models. Scores show a 95% range.
RankModelScore95% rangeVotesWon–lost–tiedWin rate
11–41,234 ±6612894–26–877%
21–71,174 ±6311878–34–669%
31–81,127 ±5911872–36–1065%
41–12Preliminary1,088 ±1043419–11–462%
52–121,073 ±679249–36–757%
62–14Preliminary1,043 ±994928–21–057%
72–15Preliminary1,032 ±1013114–15–248%
83–15Preliminary1,005 ±732713–12–252%
94–15965 ±599337–54–241%
104–16Preliminary954 ±953211–17–441%
114–16948 ±756726–39–240%
124–16Preliminary919 ±944917–32–035%
136–16Preliminary885 ±914310–29–428%
146–16864 ±915514–40–126%
157–16Preliminary843 ±102388–28–224%
1610–16824 ±758015–59–623%

How the ranking works

Signed-in CharGen users compare two outputs for one fantasy prompt with the model names hidden. Scores are a Bradley-Terry fit with 95% ranges; skips and “both poor” do not count. Full methodology

Monthly snapshot

CharGen Fantasy Arena, October 2026: a frozen, dated copy of every board with ranges and vote counts, CC BY 4.0. CSV · JSON

How to cite

CharGen Fantasy Arena, Image board, October 2026 snapshot. char-gen.com/ai-model-leaderboard/image