The AI Race
Watch the AI race unfold
Scrub the timeline to travel through 18 months of model releases. See who held the crown, who climbed the ranks, and how the benchmark landscape evolved.
Jul 202620 releases
Monthly Race Snapshot
Export or embed the live race view for the currently selected month.
More
Runner Up
Kimi K3
Moonshot AI
80.96/ 100
Releases this month
20 modelsProvider Race
Cumulative avg. top-3 score through Jul 2026Benchmark Health
More
How fresh are the benchmarks we use to score models? Green means the benchmark is actively separating models. Red means scores are bunching up or the benchmark is outdated.
Agentic
65 benchmarks62 current3 refreshing
Coding
48 benchmarks44 current3 refreshing1 stale1 saturated
Reasoning
25 benchmarks21 current1 refreshing3 stale1 saturated
Multimodal
57 benchmarks52 current5 refreshing
Knowledge
34 benchmarks27 current3 refreshing4 stale1 saturated
Multilingual
11 benchmarks10 current1 stale
Instruction Following
4 benchmarks3 current1 stale
Math
27 benchmarks21 current3 refreshing3 stale
Want deeper historical analysis?
Explore 21 months of Arena Elo ratings — crown changes, provider dominance, open-source gap tracking, and more.
LLM Leaderboard History