Other · model
Inkling-Small benchmark scores
As of 2026-11-21, Inkling-Small (Other) has measured scores on 41 benchmarks and estimated scores on 152 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 89.5% | measured |
| AA-HLE | 33.3% | measured |
| AA-SciCode | 49.7% | measured |
| AIME26 | 95.5% | measured |
| Artificial Analysis Intelligence Index | 12.9% | measured |
| CritPt | 8.3% | measured |
| GDPval-AA | 31.2% | measured |
| GPQA Diamond | 89.5% | measured |
| HLE | 47.8% | measured |
| IFBench | 82.2% | measured |
| AA-LCR | 75.7% | measured |
| LiveCodeBench v6 | 89.1% | estimated ± 2.2 pp, medium confidence |
| AA-Omniscience Accuracy | 31.8% | measured |
| SciCode | 48.7% | measured |
| Terminal-Bench 2.1 | 64.7% | measured |
| BrowseComp | 77.4% | measured |
| HLE w/ tools | 48.9% | estimated ± 5.3 pp, medium confidence |
| IFEval | 95.0% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 62.2% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 43.9% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 92.9% | estimated ± 11.8 pp, low confidence |
| AA Coding Index | 52.9% | measured |
| AA-MMMU-Pro | 74.0% | measured |
| APEX-Agents | 23.5% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 23.5% | estimated ± 4.4 pp, high confidence |
| BioMysteryBench (human-difficult) | 42.3% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 87.1% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 80.2% | measured |
| BFCL v4 | 74.6% | estimated ± 2.7 pp, high confidence |
| CyberGym | 64.7% | estimated ± 5.3 pp, low confidence |
| JobBench | 52.0% | estimated ± 7.9 pp, medium confidence |
| SkillsBench | 48.7% | estimated ± 4.1 pp, medium confidence |
| SWE-bench Pro | 55.9% | measured |
| WideResearch | 76.5% | estimated ± 3.5 pp, high confidence |
| AA Agentic Index | 25.0% | measured |
| MMLU-Pro | 85.3% | estimated ± 2.5 pp, medium confidence |
| AA-IFBench | 80.4% | estimated ± 7.4 pp, low confidence |
| FailureSensorIQ | 63.5% | estimated ± 5.0 pp, medium confidence |
| GPQA | 89.5% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 83.6% | measured |
| Vals LiveCodeBench | 85.9% | measured |
| Vals MMLU-Pro | 85.6% | measured |
| MATH-500 | 97.7% | estimated ± 3.1 pp, medium confidence |
| MMMLU | 89.2% | estimated ± 0.7 pp, medium confidence |
| MMMU | 82.4% | estimated ± 0.8 pp, high confidence |
| Chess Puzzles | 28.3% | estimated ± 4.7 pp, medium confidence |
| AIME 2025 | 96.8% | estimated ± 1.8 pp, medium confidence |
| AA MMLU-Pro | 86.1% | estimated ± 0.7 pp, high confidence |
| Gert Labs | 59.4% | estimated ± 7.1 pp, medium confidence |
| AA-AnalystAgent | 46.5% | estimated ± 3.7 pp, medium confidence |
| AA EnterpriseOps-Gym | 42.7% | measured |
| AA Harvey LAB v1.0 | 83.8% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 33.8% | estimated ± 3.6 pp, medium confidence |
| AA Terminal-Bench 2.1 | 80.1% | estimated ± 2.5 pp, medium confidence |
| ApprenticeBench | 18.9% | estimated ± 11.0 pp, low confidence |
| ARC-AGI-1 | 84.0% | measured |
| ARC-AGI-2 | 40.1% | measured |
| CursorBench 3.1 | 43.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 52.0% | estimated ± 3.6 pp, high confidence |
| EBR-bench | 0.0% | estimated ± 10.4 pp, low confidence |
| Terminal-Bench 3.0 | 7.7% | estimated ± 3.2 pp, medium confidence |
| FrontierCode 1.1 Main | 27.9% | estimated ± 4.2 pp, medium confidence |
| FrontierMath v2 (Tier 4) | 17.1% | measured |
| FrontierMath v2 (Tiers 1-3) | 46.3% | measured |
| FrontierSWE v2 | 8.5% | estimated ± 8.3 pp, medium confidence |
| Furniture Assembly | 32.9% | estimated ± 9.3 pp, low confidence |
| MaxxBench | 41.7% | estimated ± 5.7 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| Mystery Game Puzzles | 6.0% | measured |
| NYT Connections | 58.3% | estimated ± 13.8 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 69.7% | estimated ± 5.7 pp, medium confidence |
| ParseBench-1 | 61.6% | estimated ± 1.0 pp, medium confidence |
| Terminal-Bench 4.1 | 0.9% | measured |
| Terminal-Bench Hard | 52.7% | estimated ± 2.8 pp, low confidence |
| Vals SWE-bench | 82.2% | measured |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | measured |
| VulcanBench v3 | 84.2% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 49.4% | estimated ± 6.4 pp, medium confidence |
| AA Cyber Index | 16.4% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 4.3% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 49.7% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 51.8% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 40.8% | estimated ± 4.0 pp, high confidence |
| Bug Hunt Bench | 22.1% | estimated ± 10.5 pp, low confidence |
| Chartography (tools) | 79.6% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 32.5% | estimated ± 3.3 pp, medium confidence |
| CWE-bench v1 | 40.6% | estimated ± 6.4 pp, medium confidence |
| DeepSWE | 56.3% | estimated ± 7.2 pp, low confidence |
| DRACO | 76.7% | estimated ± 2.0 pp, medium confidence |
| FrontierCode 2.0 | 20.0% | estimated ± 6.7 pp, low confidence |
| FrontierPhysics | 1.1% | estimated ± 4.7 pp, medium confidence |
| HLE w/o tools | 31.6% | measured |
| OSWorld 2.1 | 46.9% | estimated ± 6.0 pp, low confidence |
| OSWorld 2.1 Offline | 8.5% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 26.0% | estimated ± 3.7 pp, high confidence |
| SpireClimb | 0.0% | estimated ± 9.3 pp, low confidence |
| StealthMark | 27.5% | measured |
| Terminal-Bench 4.0 | 10.0% | estimated ± 4.5 pp, medium confidence |
| Toolathlon-Verified | 54.4% | measured |
| VulcanBench Frontier v4 | 79.9% | estimated ± 6.8 pp, low confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| AA Terminal-Bench 4.0 | 0.5% | estimated ± 6.2 pp, low confidence |
| ARC-AGI-3 | 0.8% | estimated ± 7.2 pp, medium confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| MKA | 25.8% | estimated ± 6.4 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 44.0% | estimated ± 6.3 pp, low confidence |
| CompileBench | 53.4% | estimated ± 10.0 pp, low confidence |
| Vibe Code Bench | 49.2% | estimated ± 8.4 pp, medium confidence |
| FACTS Multimodal | 39.5% | estimated ± 4.7 pp, high confidence |
| Hermes Bench | 60.7% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 27.8% | estimated ± 8.7 pp, medium confidence |
| ParseBench-2 | 63.5% | estimated ± 5.0 pp, medium confidence |
| CharXiv | 81.3% | measured |
| CharXiv w/o tools | 77.4% | measured |
| ExploitBench | 12.6% | estimated ± 7.2 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 9.2 pp, low confidence |
| AI2D_TEST | 93.4% | estimated ± 0.9 pp, medium confidence |
| C-Eval | 89.4% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 71.6% | estimated ± 6.3 pp, low confidence |
| CountBench | 94.3% | estimated ± 2.9 pp, medium confidence |
| DeepPlanning | 49.9% | estimated ± 13.1 pp, low confidence |
| DynaMath | 86.1% | estimated ± 0.8 pp, medium confidence |
| ERQA | 58.6% | estimated ± 2.9 pp, medium confidence |
| HMMT Feb 2025 | 96.9% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 90.2% | measured |
| HMMT Nov 2025 | 94.1% | estimated ± 1.5 pp, medium confidence |
| MathVision | 82.9% | estimated ± 3.0 pp, high confidence |
| MCP Atlas | 79.6% | measured |
| MLVU (M-Avg) | 86.1% | estimated ± 1.5 pp, high confidence |
| MMAnswerBench | 83.6% | estimated ± 1.3 pp, high confidence |
| MMLU-Redux | 95.0% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 74.0% | measured |
| NL2Repo | 47.1% | estimated ± 4.7 pp, high confidence |
| PostTrainBench v1 | 27.1% | estimated ± 3.6 pp, high confidence |
| QwenClawBench | 65.6% | estimated ± 2.6 pp, medium confidence |
| RealWorldQA | 84.0% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 73.7% | estimated ± 6.8 pp, medium confidence |
| SimpleVQA | 61.6% | estimated ± 7.5 pp, medium confidence |
| SuperGPQA | 87.2% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.0 | 62.6% | estimated ± 5.8 pp, medium confidence |
| Toolathlon | 46.9% | estimated ± 4.2 pp, high confidence |
| V* | 100.0% | estimated ± 7.5 pp, medium confidence |
| Video-MME (w/o subtitle) | 82.3% | estimated ± 1.3 pp, high confidence |
| Video-MME (with subtitle) | 87.1% | estimated ± 2.9 pp, high confidence |
| VideoMMMU | 85.5% | estimated ± 1.5 pp, medium confidence |
| We-Math | 80.5% | estimated ± 7.4 pp, low confidence |
| AA LiveCodeBench | 92.9% | estimated ± 2.6 pp, medium confidence |
| HealthBench Hard | 0.8% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 80.5% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 60.8% | estimated ± 2.4 pp, high confidence |
| MedXpertQA (Text) | 52.3% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 86.7% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 79.7% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 19.3% | estimated ± 1.8 pp, high confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, medium confidence |
| PostTrainBench | 23.7% | estimated ± 3.7 pp, high confidence |
| DAYJOB | 0.0% | estimated ± 3.2 pp, medium confidence |
| DAYJOB Healthcare | 0.7% | estimated ± 4.2 pp, medium confidence |
| BioMysteryBench (human-solvable) | 82.3% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 54.6% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 42.3% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 52.7% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 41.7% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 53.3% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 16.4% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 80.7% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 24.8% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.0% | estimated ± 2.8 pp, low confidence |
| Cookie-Bench | 76.9% | estimated ± 1.3 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 34.3% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 79.4% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 24.9% | estimated ± 11.6 pp, low confidence |
| BabyVision w/ Python | 85.3% | estimated ± 3.7 pp, low confidence |
| OpenHarmony Bench v1.0 | 53.1% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 30.8% | estimated ± 9.3 pp, low confidence |
| IMOAnswerBench | 83.3% | estimated ± 5.6 pp, medium confidence |
| BabyVision | 43.1% | estimated ± 7.4 pp, low confidence |
| MMVU | 74.7% | estimated ± 2.7 pp, medium confidence |
| PerceptionBench | 55.3% | estimated ± 3.8 pp, low confidence |
| ZeroBench | 15.1% | estimated ± 7.1 pp, low confidence |
| MRCRv2 | 84.6% | estimated ± 11.3 pp, low confidence |
| LVBench | 63.7% | estimated ± 8.2 pp, low confidence |
| MMLongBench-Doc | 61.2% | estimated ± 2.6 pp, low confidence |
| OCRBench V2 | 70.0% | estimated ± 3.3 pp, high confidence |
| BioBasicsBench | 20.5% | estimated ± 2.2 pp, low confidence |
| LifeVal | 68.5% | estimated ± 1.6 pp, medium confidence |
| MMMU-Pro w/ Python | 77.3% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 5.2 pp, low confidence |
| PinchBench | 90.1% | estimated ± 3.6 pp, medium confidence |