A new model joined the thinQit Index in the 17 November 2026 refresh, led by Qwen4.
Who joined
| # | Model | Lab | Index |
|---|---|---|---|
| 21 | Qwen4 | Alibaba · Qwen | 70.1 |
Why it matters
Qwen4 sits 0.7 Index points behind #20 GLM-5.3 and 0.6 points ahead of #22 Muse Spark 1.2. Its strongest capability is Reasoning at 84.8; 4 of 7 capabilities are covered.
Also changed today
- Hy4 preview moved up from #5 to #1 on the frontier leaderboard, passing Gemini 4 Carbon, Claude Opus 5.5, Claude Fable 5.2 and Claude Fable 5.1 (Index 79.9 → 83.4).
- Gemini 4 Carbon slipped from #1 to #2 on the frontier leaderboard, passed by Claude Opus 5.5 (Index 83.2 → 83.2).
- Claude Opus 5.5 slipped from #2 to #3 on the frontier leaderboard, passed by Claude Fable 5.2 (Index 82.0 → 82.1).
- Claude Fable 5.2 slipped from #3 to #4 on the frontier leaderboard, passed by Claude Fable 5.1 (Index 81.5 → 81.5).
- Claude Fable 5.1 slipped from #4 to #5 on the frontier leaderboard, passed by Hy4 preview (Index 81.4 → 81.4).
- Beam 1.0 moved up from #10 to #9 on the local leaderboard, passing Muse Glimmer-30B (Index 65.1 → 65.1).
Also refreshed today: Hy4 preview: Blended price 0.08 · Hy4 preview: LMArena WebDev 1631.65 · Gemini 4 Carbon: LMArena Text 1538.38 · Gemini 4 Carbon: LMArena WebDev 1768.34 · Claude Opus 5.5: LMArena Text 1513.66 · Claude Opus 5.5: LMArena WebDev 1815.57 · Claude Fable 5.2: LMArena WebDev 1825.96 · Claude Fable 5.1: LMArena Text 1512.04 and 110 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Hy4 preview | Tencent | 83.4 | +3.5 |
| 2 | Gemini 4 Carbon | 83.2 | 0.0 | |
| 3 | Claude Opus 5.5 | Anthropic | 82.1 | +0.1 |
| 4 | Claude Fable 5.2 | Anthropic | 81.5 | 0.0 |
| 5 | Claude Fable 5.1 | Anthropic | 81.4 | 0.0 |
| # | Model | Params | Index |
|---|---|---|---|
| 1 | Hy4 preview | 780B (40B active) | 83.4 |
| 2 | Seed-2.0-Mini | — | 71.7 |
| 3 | GLM-5.3 | 753.3B (40B active) | 70.8 |
| 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.