Recap · 2026-09

AI leaderboard changes September 2026

As of Sep 30, 2026, 14 confirmed crown changes are recorded for September 2026.

Crowns

Confirmed crown changes

Sep 30, 2026. Vision: GPT-6 Astra and Claude Sonnet 5.5 and GPT-6.1 Sol are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-6 Astra Claude Sonnet 5.5 GPT-6.1 Sol · Vision
Sep 29, 2026. Coding › Web dev: Claude Opus 5.5 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 5.5 · Coding › Web dev
Sep 28, 2026. Math: GPT-6 Astra takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-6 Astra · Math
Sep 25, 2026. Factuality: Mimo V2.6 Pro takes the crown. First holder recorded for this category and slice. Mimo V2.6 Pro · Factuality
Sep 24, 2026. Image generation: GPT Image 2.5 Sunburst takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT Image 2.5 Sunburst · Image generation
Sep 24, 2026. Coding › Web dev: Claude Opus 5.5 and GPT-6 Astra are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 5.5 GPT-6 Astra · Coding › Web dev
Sep 22, 2026. Image edit: GPT Image 2.5 Sunburst takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT Image 2.5 Sunburst · Image edit
Sep 22, 2026. Coding › Web dev: GPT-6 Astra takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-6 Astra · Coding › Web dev
Sep 11, 2026. Reasoning: Claude Opus 4.6 and Claude Fable 5 and Claude Opus 4.7 and Claude Fable 5.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 4.6 Claude Fable 5 Claude Opus 4.7 Claude Fable 5.1 · Reasoning
Sep 11, 2026. Long context: Claude Opus 4.6 and Claude Fable 5 and Claude Fable 5.1 and Claude Opus 4.7 and Gemini 3.8 Flash are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Opus 4.6 Claude Fable 5 Claude Fable 5.1 Claude Opus 4.7 Gemini 3.8 Flash · Long context
Sep 11, 2026. General LLM: Claude Fable 5 and Claude Opus 4.6 and Claude Opus 4.7 and Claude Fable 5.1 and Muse Spark 1.2 and Gemini 3.8 Flash are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5 Claude Opus 4.6 Claude Opus 4.7 Claude Fable 5.1 Muse Spark 1.2 Gemini 3.8 Flash · General LLM
Sep 9, 2026. Vision: GPT-5.6 Sol and GPT-6 Astra are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-5.6 Sol GPT-6 Astra · Vision
Sep 8, 2026. Coding › Web dev: GPT-6 Astra and Claude Fable 5.1 are co-SOTA. Crown change confirmed by two consecutive snapshots or two independent primary sources. GPT-6 Astra Claude Fable 5.1 · Coding › Web dev
Sep 4, 2026. Coding › Web dev: Claude Fable 5.1 takes the crown. Crown change confirmed by two consecutive snapshots or two independent primary sources. Claude Fable 5.1 · Coding › Web dev

Top 3

Models that entered the top 3

Claude Fable 5 at #1 in General LLM
Claude Fable 5 at #1 in Reasoning
Claude Fable 5 at #1 in Long context
Claude Fable 5.1 at #1 in General LLM
Claude Fable 5.1 at #1 in Reasoning
Claude Fable 5.1 at #1 in Coding › Web dev
Claude Fable 5.1 at #1 in Long context
Claude Opus 4.6 at #1 in General LLM
Claude Opus 4.6 at #1 in Reasoning
Claude Opus 4.6 at #1 in Long context
Claude Opus 4.7 at #1 in General LLM
Claude Opus 4.7 at #1 in Reasoning
Claude Opus 4.7 at #1 in Long context
Claude Opus 5.5 at #1 in Coding › Web dev
Claude Sonnet 5.5 at #1 in Vision
Gemini 3.8 Flash at #1 in General LLM
Gemini 3.8 Flash at #1 in Long context
GPT Image 2.5 Sunburst at #1 in Image generation
GPT Image 2.5 Sunburst at #1 in Image edit
GPT-5.6 Sol at #1 in Vision
GPT-6 Astra at #1 in Math
GPT-6 Astra at #1 in Coding › Web dev
GPT-6 Astra at #1 in Vision
GPT-6.1 Sol at #1 in Vision
Muse Spark 1.2 at #1 in General LLM

Benchmarks

Benchmarks added or saturated

Benchmark additions for this month are still empty.