Thinking Machines
Inkling benchmark results
5 results on 5 benchmarks from 3 sources.
Also listed as: inkling · Inkling_xhigh · Inkling (xhigh)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1441 | 95 | Overall, style control on; 37744 votes; 95% CI 1437–1445“inkling” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1413 | 84 | Overall; 14358 votes; 95% CI 1407–1419“inkling” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 88.3% | 59 | Epoch AI run, accuracy; effort: xhigh | Independent run | Aug 5, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 88.9% | 73 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh | Independent run | Aug 5, 2026 |
| τ²-bench | 25.0% | 19 | banking_knowledge domain, pass^1; effort: max; submitted by Sierra; v1.0.1 | Official leaderboard | Jul 24, 2026 |
Related on this site
FAQ
Where do these Inkling scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and τ²-bench leaderboard submissions. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.