What changed on the public AI leaderboards in the 29 October 2026 refresh of the thinQit Index, and what it means for the rankings.
What changed
- Mercury 2.5 lost 10.0 Index points (24.7 → 14.7) after new results: Output speed 859.52 → 0.
- Seed-2.0-Mini moved up from #3 to #2 on the local leaderboard, passing GLM-5.3 (Index 71.7 → 71.7).
- GLM-5.3 slipped from #2 to #3 on the local leaderboard, passed by Seed-2.0-Mini (Index 72.3 → 71.1).
- Inkling Small lost 1.5 Index points (56.5 → 55.0) after new results: AA Intelligence Index 25.7 → 12.9; Output speed 236.09 → 227.84.
- DeepSeek V4 Pro lost 1.3 Index points (71.8 → 70.5) after new results: Output speed 97.09 → 74.99; AA Intelligence Index 36 → 23.1.
- Qwen3.8 27B lost 1.1 Index points (62.4 → 61.3) after new results: AA Intelligence Index 33.7 → 20.1; Output speed 48.07 → 47.15.
- DeepSeek V4.1 Flash lost 1.0 Index points (72.0 → 71.0) after new results: AA Intelligence Index 45.1 → 32.5.
- GPT-5.6 Sol moved up from #9 to #8 on the frontier leaderboard, passing Muse Spark 1.3 (Index 73.2 → 73.2).
Why it matters
Output speed feeds the Speed & price capability, which carries 5 % of the Index.
Also refreshed today: Claude Opus 5.5: AA Intelligence Index 58.4 · Claude Opus 5.5: Output speed 96.57 · Claude Fable 5.1: AA Intelligence Index 49.7 · Claude Fable 5.1: Output speed 67.85 · GPT-6 Astra: AA Intelligence Index 56.9 · GPT-6 Astra: Output speed 70.13 · Muse Spark 1.3: AA Intelligence Index 36.4 · GPT-5.6 Terra: Output speed 121.82 and 38 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 80.5 | +0.1 |
| 2 | Hy4 preview | Tencent | 78.9 | 0.0 |
| 3 | Claude Fable 5.1 | Anthropic | 78.1 | −0.2 |
| 4 | Claude Fable 5 | Anthropic | 77.9 | 0.0 |
| 5 | Seed 2.0 Pro | ByteDance Seed | 76.5 | 0.0 |
| # | Model | Params | Index |
|---|---|---|---|
| 1 | Hy4 preview | 780B (40B active) | 78.9 |
| 2 | Seed-2.0-Mini | — | 71.7 |
| 3 | GLM-5.3 | 753.3B (40B active) | 71.1 |
| 4 | GLM-5.3-Flash | 321.3B (32B active) | 70.3 |
| 5 | DeepSeek V4 Flash | 304.2B (24B active) | 70.3 |
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, LLM-Stats, 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.
