# Inkling 2 Small - BenchAudit True Index Profile

**Integrity Profile: Moderate Public Lift**

> The Verdict: Modest Legacy Lift Over Private Evaluations. Inkling 2 Small (evaluated at default effort) scores slightly higher on older public tests (53.8p) than on private, fresh evaluations (49.6p), yielding a +5.1p Low-Tier Boost across 4 domains, led by Coding & SWE (+13.8p boost) and Agentic & Enterprise (+13.6p boost).

- **Canonical URL:** https://benchaudit.org/models/inkling-2-small/
- **True Index Rank:** #24 of 44
- **Creator:** Thinking Machines
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 49.6p (10 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 53.8p (8 evals)
- **Low-Tier Boost (Matched Delta):** +5.1p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #29 | 44.1p | 3 |
| Coding & SWE | #26 | 50.0p | 4 |
| Math & Scientific Reasoning | #21 | 55.6p | 1 |

## Head-to-Head: Clean Evals vs. Legacy Benchmarks

| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | 3 (44.1p) | 2 (57.7p) | +13.6p |
| Coding & SWE | 4 (50.0p) | 3 (63.8p) | +13.8p |
| General Knowledge & QA | 2 (48.8p) | 1 (48.4p) | -0.4p |
| Math & Scientific Reasoning | 1 (55.6p) | 2 (45.1p) | -10.5p |

## Audited Benchmark Performance of Inkling 2 Small

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [SWE Atlas - Codebase QnA](https://benchaudit.org/benchmarks/swe-atlas-qna/) | Public / Aging | Coding & SWE | #4/15 | 88.1p |
| [SWE-bench Pro V2](https://benchaudit.org/benchmarks/swe-bench-pro-v2/) | Public / Aging | Coding & SWE | #2/8 | 82.9p |
| [AA-AnalystAgent](https://benchaudit.org/benchmarks/aa-analystagent/) | Private / Fresh | Agentic & Enterprise | #9/24 | 67.0p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #17/50 | 66.3p |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #11/25 | 58.3p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #13/23 | 56.8p |
| [AA-3D](https://benchaudit.org/benchmarks/aa-3d/) | Private / Fresh | Coding & SWE | #13/22 | 56.3p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #22/46 | 55.6p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #23/50 | 55.1p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #23/49 | 54.2p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #25/47 | 49.1p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #21/43 | 49.1p |
| [ARC-AGI-2](https://benchaudit.org/benchmarks/arc-agi-2/) | Private / Fresh | General Knowledge & QA | #14/22 | 48.4p |
| [MMMU-Pro](https://benchaudit.org/benchmarks/mmmu-pro/) | Public / Aging | General Knowledge & QA | #11/22 | 48.4p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #25/46 | 48.1p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #15/23 | 37.3p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #15/23 | 36.4p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #29/41 | 33.5p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #40/50 | 20.4p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #45/50 | 10.2p |
