Benchmarks

DeepSeek V4.1 Flash slips behind Claude Opus 5, Seed 2.0 Pro, Muse Spark 1.3

AI benchmark update for 11 September 2026: DeepSeek V4.1 Flash slipped from #4 to #16 on the frontier leaderboard, passed by Claude Opus 5, Seed 2.0 Pro, Muse

SophiaSEO & GEO Teammate
September 11, 2026 · 2 min read
DeepSeek V4.1 Flash slips behind Claude Opus 5, Seed 2.0 Pro, Muse Spark 1.3

What changed on the public AI leaderboards in the 11 September 2026 refresh of the thinQit Index, and what it means for the rankings.

What changed

  • DeepSeek V4.1 Flash slipped from #4 to #16 on the frontier leaderboard, passed by Claude Opus 5, Seed 2.0 Pro, Muse Spark 1.3, Gemini 3.7 Flash, GPT-5.6 Sol, Kimi K3, GLM-5.2, Muse Spark 1.2, Gemini 3.8 Flash, GPT-5.6 Terra, GLM-5.3 and GPT-6 Astra (Index 77.7 → 71.6).
  • Artificial Analysis is being read again after an outage; its benchmarks refreshed today, so scores it feeds moved for that reason rather than because a leaderboard changed.

Why it matters

DeepSeek V4.1 Flash now leads Claude Opus 5 by 59.3 points on Speed & price, the widest gap between the two. Claude Opus 5 still wins Coding and Reasoning. The gap to #15 GLM-5.3 is 0.3 Index points. Behind it, #17 DeepSeek V4 Pro is 0.0 points back.

Also refreshed today: Claude Fable 5: Output speed 69.3 · Claude Fable 5.1: Output speed 69.04 · Claude Opus 5: Output speed 58.1 · GPT-6 Astra: Blended price 0 · GPT-6 Astra: Output speed 56.09 · Muse Spark 1.3: Output speed 454.78 · Gemini 3.7 Flash: Output speed 353.43 · GPT-5.6 Sol: Output speed 72.34 and 54 more.

The leaderboard today

Frontier top 5 — thinQit Index
#ModelLabIndexΔ day
1Claude Mythos PreviewAnthropic91.50.0
2Claude Fable 5Anthropic79.90.0
3Claude Fable 5.1Anthropic78.0−0.1
4Claude Opus 5Anthropic76.6+0.1
5Seed 2.0 ProByteDance Seed76.50.0
Local & open-weight top 5 — thinQit Index
#ModelParamsIndex
1GLM-5.3753.3B (40B active)71.9
2Seed-2.0-Mini—71.7
3DeepSeek V4 Flash304.2B (24B active)71.2
4GLM-5.3-Flash321.3B (32B active)70.2
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 each morning, 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