What changed on the public AI leaderboards in the 29 September 2026 refresh of the thinQit Index, and what it means for the rankings.
What changed
- Claude Sonnet 5 gained 1.5 Index points (69.5 → 71.0) after new results: LiveBench Coding 80.68 → 91.37%; Output speed 88.54 → 81.85; LiveBench Reasoning 88.69 → 91.64%.
- GPT-5.6 Sol moved up from #8 to #7 on the frontier leaderboard, passing Kimi K3 (Index 73.3 → 73.3).
- Kimi K3 slipped from #7 to #8 on the frontier leaderboard, passed by GPT-5.6 Sol (Index 73.7 → 73.3).
Why it matters
LiveBench Coding feeds the Coding capability, which carries 25 % of the Index. The gap to #17 Gemini 3.7 Flash is 0.6 Index points. Behind it, #19 Muse Spark 1.2 is 0.4 points back.
Also refreshed today: Claude Opus 5.5: Output speed 95.32 · Claude Fable 5.1: Output speed 68.95 · Claude Fable 5.1: LMArena Vision 1287 · Muse Spark 1.3: Output speed 168.82 · Muse Spark 1.3: LMArena Vision 1290 · GPT-5.6 Sol: LMArena Vision 1287 · Kimi K3: Output speed 0 · Qwen3.8 Max: LMArena Vision 1301 and 51 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 78.5 | 0.0 |
| 2 | Claude Fable 5 | Anthropic | 78.5 | 0.0 |
| 3 | Claude Fable 5.1 | Anthropic | 76.9 | −0.1 |
| 4 | Seed 2.0 Pro | ByteDance Seed | 76.5 | 0.0 |
| 5 | Claude Opus 5 | Anthropic | 75.9 | 0.0 |
| # | Model | Params | Index |
|---|---|---|---|
| 1 | GLM-5.3 | 753.3B (40B active) | 72.1 |
| 2 | Seed-2.0-Mini | — | 71.7 |
| 3 | DeepSeek V4 Flash | 304.2B (24B active) | 71.1 |
| 4 | GLM-5.3-Flash | 321.3B (32B active) | 70.2 |
| 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: 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.
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.
