No ranking changed hands in the 15 September 2026 refresh of the thinQit Index — so here is the story the standings are telling underneath.
Standings hold
Today's run re-read 20 benchmarks across 8 sources, and no model changed rank on either board. Claude Mythos Preview (Anthropic) holds #1 at 91.5. 4 models in the frontier top 5 finished exactly where they started. That is the normal case, and it is worth recording: leaderboards that move every day are usually measuring noise.
| Benchmark | Models re-read |
|---|---|
| Blended price | 53 |
| GPQA Diamond | 52 |
| Humanity's Last Exam | 49 |
| AA Intelligence Index | 46 |
| Output speed | 46 |
| AA Coding Index | 45 |
| Terminal-Bench | 45 |
| τ²-bench | 24 |
| LiveBench Reasoning | 24 |
| LiveBench Coding | 24 |
| LiveBench Agentic Coding | 24 |
| SWE-bench Verified | 18 |
Why it matters
A flat day means the public leaderboards agreed with yesterday, not that nothing was checked — every cell above was fetched again this morning. The Index only reshuffles when a benchmark result genuinely moves, which is why a rank change here is worth reading when it does happen.
Also refreshed today: Claude Fable 5: Output speed 68.63 · Claude Fable 5.1: Output speed 69.67 · Claude Opus 5: Output speed 53.8 · Muse Spark 1.3: Output speed 261.23 · Gemini 3.7 Flash: Output speed 329.99 · GPT-5.6 Sol: Output speed 67.03 · Kimi K3: Output speed 37.49 · GLM-5.2: Output speed 168.2 and 39 more.
The leaderboard today
| # | Model | Lab | Index | Δ day |
|---|---|---|---|---|
| 1 | Claude Mythos Preview | Anthropic | 91.5 | 0.0 |
| 2 | Claude Fable 5 | Anthropic | 79.9 | 0.0 |
| 3 | Claude Fable 5.1 | Anthropic | 78.0 | 0.0 |
| 4 | Claude Opus 5 | Anthropic | 76.5 | −0.1 |
| 5 | Seed 2.0 Pro | ByteDance Seed | 76.5 | 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) | 71.0 |
| 4 | GLM-5.3-Flash | 321.3B (32B active) | 70.5 |
| 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 each morning, 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.
