Recap · 2026-07

AI leaderboard changes July 2026

As of Jul 30, 2026, 19 confirmed crown changes are recorded for July 2026.

Crowns

Confirmed crown changes

  • Jul 30, 2026. Factuality: Claude Opus 5 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 5 · Factuality
  • Jul 30, 2026. Coding › Web dev: Claude Opus 5 and Kimi K3 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 5Kimi K3 · Coding › Web dev
  • Jul 27, 2026. Reasoning: Claude Fable 5 and Claude Opus 4.6 and Claude Opus 5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6Claude Opus 5 · Reasoning
  • Jul 27, 2026. Long context: Claude Fable 5 and Claude Opus 4.6 and Claude Opus 5 and Kimi K3 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6Claude Opus 5Kimi K3 · Long context
  • Jul 27, 2026. General LLM: Claude Fable 5 and Claude Opus 5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 5 · General LLM
  • Jul 21, 2026. Long context: Claude Fable 5 and Claude Opus 4.6 and Claude Opus 4.7 and Kimi K3 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6Claude Opus 4.7Kimi K3 · Long context
  • Jul 21, 2026. Factuality: Claude Opus 4.6 and GPT-5.4 and Claude Fable 5 and GPT-5.5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 4.6GPT-5.4Claude Fable 5GPT-5.5 · Factuality
  • Jul 20, 2026. General LLM: Claude Fable 5 and Claude Opus 4.6 and Muse Spark 1.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6Muse Spark 1.1 · General LLM
  • Jul 20, 2026. Coding › Web dev: Kimi K3 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K3 · Coding › Web dev
  • Jul 20, 2026. Reasoning: Kimi K3 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K3 · Reasoning
  • Jul 20, 2026. Long context: Kimi K3 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K3 · Long context
  • Jul 20, 2026. General LLM: Kimi K3 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K3 · General LLM
  • Jul 20, 2026. Coding › Web dev: Kimi K3 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Kimi K3 · Coding › Web dev
  • Jul 16, 2026. Vision: Claude Fable 5 and GPT-5.6 Sol are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5GPT-5.6 Sol · Vision
  • Jul 14, 2026. Reasoning: Claude Fable 5 and Claude Opus 4.6 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6 · Reasoning
  • Jul 14, 2026. Factuality: Claude Fable 5 and Claude Opus 4.6 and GPT-5.4 and GPT-5.5 and Gemini 3 Pro and Muse Spark 1.1 are co-SOTA. First holder recorded for this category and slice. Claude Fable 5Claude Opus 4.6GPT-5.4GPT-5.5Gemini 3 ProMuse Spark 1.1 · Factuality
  • Jul 12, 2026. Long context: Claude Fable 5 and Claude Opus 4.6 and Claude Opus 4.7 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5Claude Opus 4.6Claude Opus 4.7 · Long context
  • Jul 12, 2026. Coding › Web dev: GPT-5.6 Sol and Claude Fable 5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5.6 SolClaude Fable 5 · Coding › Web dev
  • Jul 8, 2026. Vision: GPT-5.5 and Claude Fable 5 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5.5Claude Fable 5 · Vision
Top 3

Models that entered the top 3

Benchmarks

Benchmarks added or saturated

Benchmark additions for this month are still empty.