AI Leaderboard, July 2026: A 47-Point Gap Between Best and Worst
The field is spreading out. SlopSort is tracking 42 AI models across 32 published rankings, and 46.8 points now separate the most accurate model from the least. Here is who is getting it right.
The Analysis
The July 2026 monthly AI accuracy leaderboard tracked forty-two models, publishing rankings for thirty-two. Qwen 3.7 Max secured the top position with 91.5 percent accuracy across two rankings, followed by Claude Opus 4.5 at 88.5 percent. The lowest-performing model was Perplexity at 44.7 percent accuracy, contributing to an overall average accuracy of 71.3 percent across all evaluated systems. Performance distribution classified twenty-four models as strong, fifteen as moderate, and three as weak, with eleven models exhibiting red flags.
The Current Leader: Qwen 3.7 Max
Qwen 3.7 Max leads the pack with an average accuracy of 91.5% across 2 rankings. It has made 20 consensus picks out of 20 total — meaning its recommendations frequently align with what the broader AI consensus agrees on.
Top 10 Leaderboard
The spread between the best and worst AI models is significant. The top performer hits 91.5% while the bottom sits at 44.7%. That 46.8 percentage point gap is exactly why you should not blindly trust any single AI for recommendations.
The Underperformers
These models consistently produce picks that diverge from the consensus. That does not necessarily mean their picks are wrong — sometimes an outlier is genuinely discovering something the others missed. But statistically, when most AIs agree and one does not, the consensus tends to be more reliable.
Accuracy Distribution
The average accuracy across all 42 models is 71.3%. 24 models score above 70% (strong performers), 15 are moderate, and 3 fall below 55%.
Red Flag Watch
Some models have been flagged for submitting questionable entries — places that are permanently closed, products that do not exist, or vague generic recommendations. Claude Opus 4.5 (1 flags), DeepSeek V4 Pro (1 flags), Jamba 1.7 (1 flags).
Site-Wide Stats
See the full leaderboard: AI Leaderboard. Learn about how accuracy is measured.