Claude Opus 5.5 vs GPT-6 Sol

Two models head to head, judged by real players in the Playgama AI sandbox. Part of the AI Game Index.

Key findings

Claude Opus 5.5GPT-6 Sol

Share of new games8.1× more

Claude Opus 5.5: 89%

GPT-6 Sol: 11%

Likes per 1,000 plays1.3× more

Claude Opus 5.5: 43

GPT-6 Sol: 55

Median play timeAbout even

Claude Opus 5.5: 4 min 8 s

GPT-6 Sol: 4 min 11 s

Head to head

Claude Opus 5.5 vs GPT-6 Sol, head to head
Claude Opus 5.5GPT-6 Sol
Share of new games, Oct 18 – Nov 1689%11%
Share of new games, last 7 days87%13%
Play time, median game, all time4 min 8 s4 min 11 s
Likes per 1,000 plays, all time4355

The higher figure is lit. Shares count the two models’ games only; play time and likes are all-time medians of games with 20+ plays.

Share, play time and likes

Shares are of the pair’s new games, so the two make 100%; other models are left out.

Share of new games by model

7-day average of the daily shares.

Table data
Share of new games by model, per day
DayClaude Opus 5.5GPT-6 Sol
Oct 1890.9%9.1%
Oct 1989%11%
Oct 2089%11%
Oct 2182%18%
Oct 2286%14%
Oct 2396.1%3.9%
Oct 2485%15%
Oct 2590%10%
Oct 2684%16%
Oct 2791.5%8.5%
Oct 2889%11%
Oct 2981%19%
Oct 3090%10%
Oct 3192.1%7.9%
Nov 186%14%
Nov 290.5%9.5%
Nov 390.6%9.4%
Nov 498.0%2.0%
Nov 578%22%
Nov 698.1%1.9%
Nov 798.0%2.0%
Nov 894.8%5.2%
Nov 994.2%5.8%
Nov 1093.3%6.7%
Nov 1188%12%
Nov 1286%14%
Nov 1389%11%
Nov 1490.4%9.6%
Nov 1581%19%
Nov 1684%16%

Play time and likes by model

Each figure is the model’s median game among those with 20 plays or more, so one hit cannot carry a row. How it’s measured

Model Sort by
  • GPT-6 Sol
    4 min 11 s 55 likes
  • Claude Opus 5.5
    4 min 8 s 43 likes
  • 20th to 80th percentile of the games
  • median game
Table data
Play time and likes by model
ModelMedian game20th to 80th percentile10th to 90th percentileLikes per 1,0001k plays
GPT-6 Sol (OpenAI)4 min 11 s2 min 50 s – 7 min 44 s2 min 31 s – 12 min 3 s55
Claude Opus 5.5 (Anthropic)4 min 8 s3 min 1 s – 6 min 11 s2 min 41 s – 8 min 2 s43

How the comparison is calculated

Where the games come from
Every game is an AI-built web game published to the Playgama AI sandbox, by hand or through Playgama MCP from an agent. Developers name the agent and model when they publish; the answers are self-reported and not verified.
Share of new games
Each day’s new games built with Claude Opus 5.5 or GPT-6 Sol, split between the two (100% together); every other model is in the AI Game Index. A game counts once, on the day it was first published, even if later taken down. The chart shows a 7-day average; the table under it has each day.
Period
Shares cover the period above the title: at most the last 30 closed days, none before September 28, 2026, the first full week of model answers.
Play time
The all-time average length of a game’s plays (sessions of 30 seconds or more), counted by Playgama Bridge, the SDK inside the game. A row shows the median game and the spread around it.
Likes per 1,000 plays
A game’s all-time likes on its sandbox page per 1,000 all-time plays. A row is the median game; a game with no likes counts as zero.
Minimum sample
A game is measured from 20 plays; a model is rated from 15 measured games.
Model versions
The form has asked for the exact version only since October 12, 2026, so most games name just the model. Here every Claude Opus game counts as Claude Opus 5.5 (97% of those naming a version give it), and every OpenAI Sol game as GPT-6 Sol.
Updates
Daily, with the AI Game Index: a day closes at 00:00 UTC and lands here that morning.

See every model

The AI Game Index ranks every agent and model, updated daily.

Built a game with AI? Publish it with Playgama MCP and your model joins the index.