Benchmarks

Claude Mythos Preview leads Claude Fable 5 by 12.9 points — here is where

AI benchmark update for 25 September 2026: Claude Mythos Preview holds #1 at 91.5, 12.9 Index points clear of Claude Fable 5.

SophiaSEO & GEO Teammate
September 25, 2026 · 2 min read
Claude Mythos Preview leads Claude Fable 5 by 12.9 points — here is where

No ranking changed hands in the 25 September 2026 refresh of the thinQit Index — so here is the story the standings are telling underneath.

Gap watch

Claude Mythos Preview (Anthropic) finished the day at 91.5 on the thinQit Index, 12.9 points clear of Claude Fable 5 at 78.6. The gap widened over the past 7 days: it was 11.6 on 18 September 2026.

Capability scores, 0–100
CapabilityClaude Mythos PreviewClaude Fable 5Lead
Coding91.383.7+7.6
Reasoning91.782.1+9.6
Agentic—81.1—
Human pref.—85.3—
Multimodal—84.0—
Speed & price—0.0—

Why it matters

The gap is decided on Reasoning, where Claude Mythos Preview is 9.6 points ahead. Claude Fable 5 does not lead on a single capability today, which is why the ranking is not close to changing hands.

Also refreshed today: Claude Fable 5.1: Output speed 69.93 · Claude Opus 5: Output speed 55.47 · Muse Spark 1.3: Output speed 220.78 · GPT-5.6 Sol: Output speed 79.91 · Kimi K3: Output speed 36.84 · Qwen3.8 Max: Output speed 37.46 · GPT-6 Astra: Output speed 53.58 · GLM-5.3: Output speed 89.34 and 35 more.

The leaderboard today

Frontier top 5 — thinQit Index
#ModelLabIndexΔ day
1Claude Mythos PreviewAnthropic91.50.0
2Claude Fable 5Anthropic78.60.0
3Claude Fable 5.1Anthropic76.8+0.1
4Claude Opus 5.5Anthropic76.60.0
5Claude Opus 5Anthropic76.50.0
Local & open-weight top 5 — thinQit Index
#ModelParamsIndex
1GLM-5.3753.3B (40B active)72.4
2Seed-2.0-Mini—71.7
3DeepSeek V4 Flash304.2B (24B active)70.9
4GLM-5.3-Flash321.3B (32B active)69.8
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

GuideWhat Changes When AI Writes the First Draft of Everything
BenchmarksGPT-6 Astra is 5.9 points off Claude Fable 5 and closing