Other · model
Inkling benchmark scores
As of 2026-10-07, Inkling (Other) has measured scores on 39 benchmarks and estimated scores on 89 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 87.2% | measured |
| AA-HLE | 31.9% | measured |
| AA-SciCode | 47.0% | measured |
| AIME26 | 97.1% | measured |
| Artificial Analysis Intelligence Index | 25.0% | measured |
| CritPt | 5.4% | measured |
| GDPval-AA | 28.9% | measured |
| GPQA Diamond | 87.9% | measured |
| HLE | 46.0% | measured |
| IFBench | 79.8% | measured |
| AA-LCR | 77.3% | measured |
| LiveCodeBench v6 | 86.6% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 41.6% | measured |
| SciCode | 47.7% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 63.8% | measured |
| BrowseComp | 77.1% | measured |
| HLE w/ tools | 49.8% | estimated ± 4.6 pp, high confidence |
| IFEval | 92.8% | estimated ± 3.5 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 45.8% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 91.1% | estimated ± 2.4 pp, medium confidence |
| AA Coding Index | 52.1% | measured |
| AA-MMMU-Pro | 73.5% | measured |
| APEX-Agents | 29.1% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 22.9% | estimated ± 4.6 pp, high confidence |
| BioMysteryBench (human-difficult) | 41.8% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 86.8% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 77.6% | measured |
| AutomationBench | 44.9% | estimated ± 7.0 pp, low confidence |
| BFCL v4 | 74.9% | estimated ± 2.6 pp, high confidence |
| CyberGym | 75.4% | estimated ± 4.6 pp, high confidence |
| JobBench | 44.5% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 54.3% | measured |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 76.5% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 24.3% | measured |
| MMLU-Pro | 85.2% | estimated ± 2.5 pp, medium confidence |
| GPQA | 87.9% | measured |
| AA-IFBench | 80.3% | estimated ± 8.5 pp, medium confidence |
| Gert Labs | 58.1% | estimated ± 7.4 pp, medium confidence |
| AA-AnalystAgent | 23.8% | measured |
| AA EnterpriseOps-Gym | 38.0% | measured |
| AA Harvey LAB | 83.4% | estimated ± 1.2 pp, medium confidence |
| ARC-AGI-1 | 85.7% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 48.0% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 36.6% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 49.1% | estimated ± 3.6 pp, medium confidence |
| Terminal-Bench 3.0 | 1.5% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 17.4% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 4.1% | measured |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| OSWorld-Verified | 68.7% | estimated ± 5.4 pp, medium confidence |
| Vals GPQA Diamond | 87.1% | measured |
| Vals LiveCodeBench | 85.5% | measured |
| Vals MMLU-Pro | 86.3% | measured |
| Vals SWE-bench | 77.6% | measured |
| Terminal-Bench 2.1 (Vals AI) | 47.6% | measured |
| VulcanBench v3 | 83.9% | estimated ± 5.6 pp, low confidence |
| AA AutomationBench | 5.0% | measured |
| GDP.pdf | 12.8% | measured |
| AA ITBench | 42.1% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 29.1% | measured |
| AA Terminal-Bench 2.1 | 55.1% | measured |
| AA Terminal-Bench 4.0 | 1.0% | measured |
| CursorBench 4.0 | 17.2% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 37.0% | measured |
| DeepSWE | 40.8% | estimated ± 4.2 pp, medium confidence |
| HLE w/o tools | 30.0% | measured |
| OSWorld 2.0 | 6.2% | estimated ± 13.3 pp, low confidence |
| PostTrainBench v1.1 | 23.4% | estimated ± 2.7 pp, high confidence |
| Terminal-Bench 4.0 | 5.0% | estimated ± 5.1 pp, low confidence |
| Terminal-Bench-Science 0.1 | 0.0% | estimated ± 4.1 pp, low confidence |
| Toolathlon-Verified | 71.0% | estimated ± 1.9 pp, low confidence |
| Vibe Code Bench | 18.6% | estimated ± 8.1 pp, medium confidence |
| CharXiv | 82.0% | measured |
| CharXiv w/o tools | 78.1% | measured |
| ExploitGym | 13.7% | estimated ± 5.0 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 69.3% | estimated ± 5.7 pp, medium confidence |
| DeepPlanning | 47.2% | estimated ± 13.1 pp, low confidence |
| HMMT Feb 2025 | 97.6% | estimated ± 1.9 pp, low confidence |
| HMMT Feb 2026 | 88.9% | estimated ± 4.0 pp, high confidence |
| MathVision | 82.0% | estimated ± 2.1 pp, low confidence |
| MCP Atlas | 74.1% | measured |
| MCP-Tasks | 77.0% | estimated ± 0.6 pp, low confidence |
| MMAnswerBench | 86.5% | estimated ± 1.3 pp, high confidence |
| MMLU-Redux | 96.8% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 73.5% | measured |
| NL2Repo | 44.4% | estimated ± 4.7 pp, high confidence |
| QwenClawBench | 61.8% | estimated ± 2.6 pp, high confidence |
| ScreenSpot Pro | 75.2% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 82.0% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.0 | 56.7% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 50.2% | estimated ± 3.5 pp, high confidence |
| VideoMMMU | 84.1% | estimated ± 1.0 pp, high confidence |
| ERQA | 67.1% | estimated ± 3.7 pp, high confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 79.1% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 59.6% | estimated ± 2.4 pp, high confidence |
| MedXpertQA (Text) | 48.1% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 86.2% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 77.3% | estimated ± 2.4 pp, medium confidence |
| ResearchClawBench | 18.5% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 60.9% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| DRACO | 73.4% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 26.4% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 41.2% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 56.6% | estimated ± 1.3 pp, medium confidence |
| HealthBench Professional (raw) | 52.1% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 81.1% | estimated ± 1.8 pp, low confidence |
| AIME 2025 | 97.5% | estimated ± 1.5 pp, low confidence |
| MMMU | 81.8% | estimated ± 0.9 pp, high confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| Agents' Last Exam | 28.5% | estimated ± 6.3 pp, medium confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, high confidence |
| SimpleVQA | 67.6% | estimated ± 7.8 pp, low confidence |
| MMMLU | 89.0% | estimated ± 1.1 pp, medium confidence |
| MMLU | 93.7% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 75.1% | estimated ± 0.6 pp, high confidence |
| MATH-500 | 97.9% | estimated ± 3.1 pp, low confidence |
| MathVision w/ Python | 76.8% | estimated ± 0.9 pp, low confidence |
| RealWorldQA | 85.6% | estimated ± 1.1 pp, medium confidence |
| Video-MME (with subtitle) | 87.8% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 60.5% | estimated ± 5.9 pp, low confidence |