Inkling 2 Small (XHigh): benchmark scores, price and ranking
Inkling 2 Small (XHigh) from Thinking Machines ranks #99 of 827 LLMs on the LLMs Tiger aggregate benchmark score (52.1), based on 3 benchmark results captured up to 2026-11-18.
- Organisation
- Thinking Machines
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-11-05 (source: epoch)
- Cheapest API price
- $0.300 in / $1.00 out per million tokens (via nebius, observed 2026-11-18T15:47Z)
- Aggregate rank
- #99 of 827 (score 52.1)
Relative to other models, Inkling 2 Small (XHigh) is strongest on ARC-AGI-2 (#19 of 97) and weakest on FrontierSWE (#17 of 24).
Across the 3 benchmarks where at least ten models are scored, Inkling 2 Small (XHigh) is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.300 per million tokens, is lower than that of 58% of the 443 models with a listed price.
Inkling 2 Small (XHigh) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ARC-AGI-2 | 81.7% | #19 of 97 | ARC Prize official leaderboard | 2026-11-18 |
| GDP.pdf | 43.6% | #14 of 37 | Epoch AI Benchmarking Hub | 2026-11-18 |
| FrontierSWE | 25.1% | #17 of 24 | Epoch AI Benchmarking Hub | 2026-11-18 |
About Inkling 2 Small (XHigh)
Inkling 2 Small (XHigh) is an open-weight model that can run on your own hardware from Thinking Machines. It was released on 2026-11-05, according to Epoch AI. The cheapest API listing we track charges $0.300 per million input tokens and $1.00 per million output tokens, through nebius. We hold 3 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where Inkling 2 Small (XHigh) stands
On our aggregate score, Inkling 2 Small (XHigh) is #99 of 827 ranked models, in the top quarter. Its score is 52.1; the scale is centred on 50, so it sits 2.1 points above the typical model. That beats 88% of the ranked field. Among the 3 ranked Thinking Machines models it is #1. The next one down is Inkling Small (xhigh) at 49.2.
Inkling 2 Small (XHigh), benchmark by benchmark
ARC-AGI-2 puts Inkling 2 Small (XHigh) at 81.7%, #19 of 97. That beats 80% of the models tested, but 14.2 points short of GPT-6.2 Astra (max) (95.8%). The results either side are GPT-5.6 Terra (max) (83.9%) and DeepSeek V4.1 Flash 1017 (max) (78.1%). It covers abstract reasoning, ARC Prize public eval set. The board median is 40.1%, so Inkling 2 Small (XHigh) is 41.5 points above it. Source: ARC Prize official leaderboard, captured 2026-11-18.
On GDP.pdf, Inkling 2 Small (XHigh) reaches 43.6%. It ranks #14 of 37, ahead of 62% of the field, and 12.8 points behind Gemini 4 Carbon (high) at 56.4%. The results either side are Gemini 3.8 Flash (high) (44.2%) and Qwen3.8 Max (xhigh) (42.8%). It covers economically valuable document tasks. The board median is 32.8%, so Inkling 2 Small (XHigh) is 10.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Inkling 2 Small (XHigh) lands below the middle on FrontierSWE: 25.1%, #17 of 24, with 67% of the field scoring higher. Claude Fable 5.2 (max) leads at 69.9%; the closest result above is Grok 4.6 (xhigh) at 25.3%. It covers hard multi-hour software engineering. The board median is 29.8%, so Inkling 2 Small (XHigh) is 4.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Strengths and weaknesses
Inkling 2 Small (XHigh) has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Price and value
The median input price across the 443 priced models is $0.482 per million tokens, so Inkling 2 Small (XHigh) costs less than the typical listing. Models that score within 1.5 points or better and cost less: GLM-5.2 (high) ($0.0070, 51.6), DeepSeek V4.1 Flash 1017 (max) ($0.036, 55.5), DeepSeek V4 Flash 0731 (max) ($0.060, 52.3). Similar scores cost more on qwen-2.5-72b-instruct ($0.380) and DeepSeek R1 (0528) ($0.400).
Release history
The Thinking Machines model released before it was Inkling (xhigh) on 2026-07-15, which scores 47.6.
Reading these numbers
The 3 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (2), ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 2 from datasets or third-party runs. The leaderboard also lists 2 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 3 results the aggregate rank can move a lot when one new score arrives.
Inkling 2 Small (XHigh) is also listed at 2 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #96 gpt-5.2-2025-12-11-high (52.1)
- #97 Darwin-397B-ZTC (52.1)
- #98 Claude Sonnet 5 (max) (52.1)
- #100 GPT-6 Luna (max) (52.1)
- #101 Antigravity CLI + Gemini 4 Argon (52.1)
- #102 GPT-5.2 Codex (52.0)
More from Thinking Machines
- Inkling Small (xhigh) (#323, 49.2)
- Inkling (xhigh) (#478, 47.6)
Compare it on the live leaderboard → · How the aggregate score works