Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Inkling?

114 SI-IQ · 90% interval 110–117
Rank 53 of 80 ranked models · Plausible rank range 40–64

Inkling is a model from Thinking Machines, released on Jul 15, 2026. Its SI-IQ is 114 (90% interval 110–117), estimated from 7 benchmark results by 2 independent evaluators. Its strongest area is Knowledge and its weakest is Math.

Facts

Developer
Thinking Machines
Released
Jul 15, 2026
Access
Open weights (restricted licence)
Benchmarks used
7 results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

6080100120140160Math113Knowledge117

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
Chess Puzzles Reasoning 21.0% 113 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tier 4 Math 4.9% 113 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 33.3% 113 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 88.9% 115 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 88.3% 120 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 81.8% 114 OpenRouter thinkingmachines/inkling-20260715
BaseTen · median over providers (2 of 2 rows), lower median
Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 40.3% 120 Epoch AI Inkling_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run) Agents 67.6% 116 OpenRouter thinkingmachines/inkling-20260715
BaseTen, DeepInfra, Together · median over providers (3 of 3 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Inkling has a rating of 1,441 (1,437–1,445) from 40,648 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

ModelSI-IQ
Qwen3.5 397B-A17BAlibaba114Inkling vs Qwen3.5 397B-A17B
Claude Sonnet 4.6Anthropic113Inkling vs Claude Sonnet 4.6
Claude Opus 4.5Anthropic115Inkling vs Claude Opus 4.5
Qwen3.7-PlusAlibaba115Inkling vs Qwen3.7-Plus
Qwen3.6 27BAlibaba115Inkling vs Qwen3.6 27B

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..