A new model joined the thinQit Index in the 12 November 2026 refresh, led by Claude Fable 5.2.
Who joined
| # | Model | Lab | Index |
|---|---|---|---|
| 3 | Claude Fable 5.2 | Anthropic | 81.5 |
Why it matters
Claude Fable 5.2 sits 0.5 Index points behind #2 Claude Opus 5.5 and 0.1 points ahead of #4 Claude Fable 5.1. Its strongest capability is Reasoning at 95.3; 4 of 7 capabilities are covered.
Also changed today
- Gemini 4 Carbon lost 3.5 Index points (86.7 → 83.2) after new results: LiveBench Agentic new at 72.7%; LiveBench Reasoning new at 90.6%; LiveBench Coding new at 91%.
- Claude Fable 5.1 slipped from #3 to #4 on the frontier leaderboard, passed by Hy4 preview (Index 81.5 → 81.4).
- Hy4 preview slipped from #4 to #5 on the frontier leaderboard, passed by Muse Wonder Full (Index 79.9 → 79.9).
- Muse Wonder Full slipped from #5 to #6 on the frontier leaderboard, passed by Gemini 4 Argon (Index 79.4 → 79.4).
- Gemini 4 Argon slipped from #6 to #7 on the frontier leaderboard, passed by Claude Opus 5 (Index 78.3 → 78.3).
- Gemini 3.8 Flash gained 1.0 Index points (68.1 → 69.1) after new results: LiveBench Coding 65.7 → 73.3%; LMArena WebDev 1583.8 → 1582.65.
Also refreshed today: Gemini 4 Carbon: LMArena WebDev 1768.16 · Gemini 4 Carbon: LiveBench Agentic 72.7% · Gemini 4 Carbon: LiveBench Reasoning 90.6% · Gemini 4 Carbon: LiveBench Coding 91% · Claude Opus 5.5: LMArena WebDev 1814.28 · Claude Fable 5.2: LMArena WebDev 1835.76 · Claude Fable 5.2: Humanity's Last Exam 73.2% · Claude Fable 5.2: LiveBench Agentic 82.9% and 59 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Gemini 4 Carbon | 83.2 | −3.5 | |
| 2 | Claude Opus 5.5 | Anthropic | 82.0 | 0.0 |
| 3 | Claude Fable 5.2 | Anthropic | 81.5 | — |
| 4 | Claude Fable 5.1 | Anthropic | 81.4 | −0.1 |
| 5 | Hy4 preview | Tencent | 79.9 | 0.0 |
| # | Model | Params | Index |
|---|---|---|---|
| 1 | Hy4 preview | 780B (40B active) | 79.9 |
| 2 | Seed-2.0-Mini | — | 71.7 |
| 3 | GLM-5.3 | 753.3B (40B active) | 70.9 |
| 4 | DeepSeek V4 Flash | 304.2B (24B active) | 69.6 |
| 5 | Seed-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: 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.
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.
