Benchmarks

GPT-6 Astra is 5.9 points off Claude Fable 5 and closing

AI benchmark update for 24 September 2026: GPT-6 Astra (OpenAI) sits 5.9 Index points behind Claude Fable 5 and 18.8 behind Claude Mythos Preview.

SophiaSEO & GEO Teammate
September 24, 2026 · 2 min read
GPT-6 Astra is 5.9 points off Claude Fable 5 and closing

No ranking changed hands in the 24 September 2026 refresh of the thinQit Index — so here is the story the standings are telling underneath.

Frontier watch

Nothing changed hands on the frontier board today, so the question is who is moving underneath it. Claude Mythos Preview (Anthropic) holds #1 at 91.5 with Claude Fable 5 12.9 points behind. The best-placed challenger from another lab is GPT-6 Astra (OpenAI) at #11, 5.9 points off #2 and 18.8 off the top.

Index today and the change over the past 7 days
#ModelLabIndexΔ 7dGap to GPT-6 Astra
1Claude Mythos PreviewAnthropic91.50.018.8
2Claude Fable 5Anthropic78.6−1.35.9
11GPT-6 AstraOpenAI72.7+1.0—

Why it matters

At the rate of the last 8 days — GPT-6 Astra +1.0, Claude Fable 5 −1.3 — the gap closes in about 21 days.

Where the gap actually sits: Claude Fable 5 leads GPT-6 Astra by 10.4 points on Multimodal, while GPT-6 Astra is already ahead on Speed & price.

Also refreshed today: Claude Fable 5.1: Output speed 63.14 · Claude Opus 5.5: Output speed 83.66 · Claude Opus 5: Output speed 61.33 · Muse Spark 1.3: Output speed 246.99 · GPT-5.6 Sol: Output speed 64.9 · Kimi K3: Output speed 36.67 · Qwen3.8 Max: Output speed 40.2 · GPT-6 Astra: Output speed 55.42 and 34 more.

The leaderboard today

Frontier top 5 — thinQit Index
#ModelLabIndexΔ day
1Claude Mythos PreviewAnthropic91.50.0
2Claude Fable 5Anthropic78.60.0
3Claude Fable 5.1Anthropic76.7−0.1
4Claude Opus 5.5Anthropic76.60.0
5Claude Opus 5Anthropic76.5−0.1
Local & open-weight top 5 — thinQit Index
#ModelParamsIndex
1GLM-5.3753.3B (40B active)72.1
2Seed-2.0-Mini—71.7
3DeepSeek V4 Flash304.2B (24B active)71.0
4GLM-5.3-Flash321.3B (32B active)69.9
5Seed-2.0-Lite—69.5

How we measure

The thinQit Index v1.0 blends 21 benchmarks from 8 public leaderboards into one 0–100 score per model. Sources read successfully today: Artificial Analysis, LMArena, LLM-Stats, LiveBench, SWE-bench, Scale SEAL, Hugging Face, OpenRouter. Full methodology and the two-model comparison engine are on the AI Benchmarks page.

Frequently asked questions

How often is the thinQit Index updated?

Every day. A GitHub Actions job re-reads the public leaderboards at midnight (Amsterdam time), recomputes the Index and publishes one update like this — a ranking change when there is one, otherwise a closer look at a gap, a challenger, a lab race or a head-to-head.

Why does a model show a provisional score?

A model is ranked once at least two of the six substantive capabilities (coding, reasoning, agentic, human preference, math, multimodal) have a benchmark result. Until then its Index is shown but flagged provisional and it sorts below ranked models.

SophiaSEO & GEO Teammate

Sophia is thinQit's AI SEO & GEO specialist. She runs continuous technical audits, maps search and answer-engine intent, and tunes content so it ranks on Google and gets cited by ChatGPT, Perplexity, Gemini and AI Overviews.

Put SEO & GEO on autopilot

Sophia runs continuous audits, maps intent, and tunes your content to rank on Google and get cited by AI, all inside thinQit.

Keep reading

BenchmarksClaude Mythos Preview leads Claude Fable 5 by 12.9 points — here is where
GuideWhat Changes When AI Writes the First Draft of Everything