What changed on the public AI leaderboards in the 4 September 2026 refresh of the thinQit Index, and what it means for the rankings.
What changed
- Claude Fable 5 moved up from #2 to #1 on the frontier leaderboard (Index 80.8 → 80.9).
- Claude Fable 5.1 moved down from #1 to #2 on the frontier leaderboard (Index 81.0 → 79.4).
- Muse Spark 1.2 moved up from #9 to #8 on the frontier leaderboard (Index 73.2 → 73.6).
- GLM-5.3 moved down from #8 to #9 on the frontier leaderboard (Index 73.4 → 73.4).
Also refreshed today: Claude Fable 5: Output speed 66.93 · Claude Fable 5.1: Output speed 70.31 · Claude Fable 5.1: SEAL · HLE 46.5% · Claude Opus 5: Output speed 48.98 · Gemini 3.7 Flash: Output speed 297.32 · Kimi K3: Output speed 37.89 · GPT-5.6 Sol: Output speed 82.03 · GPT-5.6 Terra: Output speed 100.63 and 27 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 80.9 | +0.1 |
| 2 | Claude Fable 5.1 | Anthropic | 79.4 | -1.6 |
| 3 | Claude Opus 5 | Anthropic | 77.6 | 0.0 |
| 4 | Gemini 3.7 Flash | 75.6 | 0.0 | |
| 5 | Kimi K3 | Moonshot AI | 75.2 | 0.0 |
| # | Model | Params | Index |
|---|---|---|---|
| 1 | GLM-5.3 | 753.3B (40B active) | 73.4 |
| 2 | DeepSeek V4 Flash | 304.2B (24B active) | 71.6 |
| 3 | GLM-5.3-Flash | 321.3B (32B active) | 71.0 |
| 4 | Qwen3.8 2.4T-A95B | 2400B (95B active) | 70.5 |
| 5 | Qwen3.8-Flash-Next | 177B (12B active) | 69.2 |
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, recomputes the Index and publishes a news post like this one only when something changed.
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.
