All AI performance rankings
AI rankings for classification and judgment
Which AI is best at classification and judgment?
As of Nov 2026: #1 Decider V1.2, #2
Perplexity Decider v1.1 27B, #3
d1.2-ultra. A classification and judgment performance ranking of 34 AI models across 8 evaluations, including AIB DecisionBench-KJ · AIB DecisionBench-Game · AIB DecisionBench-Agent.
Last updated 2026-11-21 · AIB compiles and analyzes scores from many benchmarks to produce its own independent ranking.
Learn more about this evaluation
- 🥇PerplexityDecider V1.282.356.492.2
- 🥈PerplexityPerplexity Decider v1.1 27B81.752.792.2
- 🥉Liquid AId1.2-ultra81.650.193.9
- #4Liquid AID1 Ultra81.538.192.8
- #5Liquid AId1.280.655.493.4
- #6Liquid AId1.179.948.291.1
- #7GoogleGemini Decision 179.866.5—
- #8TypeSafeJev 1.1478.754.190.0
- #9TypeSafeJev 1.1378.658.289.2
- #10InceptionMercury Decide77.711.186.0
Top 7 within the margin of error · effectively tied · Half of models ≤ 75.3Last updated 2026-11-21
Recent ranking changes
Frequently asked questions
- How is the ranking decided?
- Models are ordered by their AIB DecisionBench-KJ score. We do not make a blended score from several tests. Pick another test above the table (AIB DecisionBench-Game, AIB DecisionBench-Agent) to reorder by that test.
- Where do the scores come from?
- We take the scores each test publishes, as they are. This ranking covers 8 tests and 34 AI models, and scores the AI maker reported itself are marked with a dotted underline.
- How often does the ranking change?
- We check test results every day and recalculate the ranking every hour. Results were last collected on 2026-11-21. Past changes are listed under Recent ranking changes.
- Which subscriptions include the top-ranked models?
- The plan comparison shows which models each ChatGPT, Claude, Gemini, Grok and other plan includes, with monthly prices and usage limits taken from the official pricing pages.
- What if a service is slow or down?
- The status page shows whether ChatGPT, Claude, Gemini, Grok and others are working right now and how many outages they had recently, based on their official status pages.