Other · model
Beam benchmark scores
As of 2026-10-07, Beam (Other) has measured scores on 14 benchmarks and estimated scores on 81 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 89.3% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 36.6% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 49.2% | estimated ± 3.1 pp, high confidence |
| AIME26 | 97.8% | measured |
| Artificial Analysis Intelligence Index | 30.8% | estimated ± 5.1 pp, medium confidence |
| CritPt | 12.2% | estimated ± 4.9 pp, high confidence |
| GDPval-AA | 35.5% | estimated ± 8.4 pp, medium confidence |
| GPQA Diamond | 90.5% | measured |
| HLE | 45.9% | estimated ± 5.7 pp, medium confidence |
| IFBench | 79.7% | measured |
| AA-LCR | 73.3% | estimated ± 7.0 pp, low confidence |
| LiveCodeBench v6 | 90.9% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 38.2% | estimated ± 8.6 pp, medium confidence |
| SciCode | 49.7% | measured |
| Terminal-Bench 2.1 | 80.1% | measured |
| BrowseComp | 77.4% | measured |
| HLE w/ tools | 50.3% | estimated ± 4.6 pp, high confidence |
| IFEval | 92.8% | estimated ± 3.5 pp, high confidence |
| LongBench v2 | 65.5% | measured |
| VITA-Bench | 47.7% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 68.3% | estimated ± 2.5 pp, high confidence |
| APEX-Agents | 32.8% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 23.2% | estimated ± 4.6 pp, high confidence |
| DeepSearchQA | 80.1% | measured |
| SWE-bench Verified | 80.9% | measured |
| AutomationBench | 27.1% | estimated ± 10.3 pp, low confidence |
| CyberGym | 75.6% | estimated ± 4.6 pp, high confidence |
| JobBench | 49.1% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 65.5% | measured |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 76.6% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 31.1% | estimated ± 8.2 pp, medium confidence |
| MMLU-Pro | 85.5% | estimated ± 2.5 pp, medium confidence |
| GPQA | 90.5% | estimated ± 0.4 pp, high confidence |
| AA-IFBench | 80.3% | estimated ± 8.5 pp, medium confidence |
| Gert Labs | 58.5% | estimated ± 7.4 pp, medium confidence |
| AA-AnalystAgent | 23.5% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 40.1% | estimated ± 6.9 pp, low confidence |
| AA Harvey LAB | 89.9% | estimated ± 9.8 pp, low confidence |
| ApprenticeBench | 11.8% | estimated ± 10.1 pp, low confidence |
| ARC-AGI-1 | 89.9% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 57.9% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 58.2% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 64.0% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 13.5% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 28.1% | estimated ± 2.7 pp, medium confidence |
| FrontierSWE v2 | 24.9% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 69.1% | estimated ± 5.4 pp, medium confidence |
| Vals GPQA Diamond | 89.8% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 86.2% | estimated ± 0.8 pp, medium confidence |
| Vals MMLU-Pro | 86.9% | estimated ± 1.6 pp, high confidence |
| Vals SWE-bench | 74.6% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | estimated ± 7.4 pp, medium confidence |
| AA AutomationBench | 5.9% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.3% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 46.4% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 25.7% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.6% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 18.7% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 39.7% | estimated ± 3.6 pp, high confidence |
| DeepSWE | 44.4% | measured |
| HLE w/o tools | 36.2% | measured |
| OSWorld 2.0 | 17.7% | estimated ± 13.8 pp, low confidence |
| PostTrainBench v1.1 | 29.1% | estimated ± 4.7 pp, high confidence |
| SWE Multilingual | 78.0% | measured |
| Toolathlon-Verified | 61.9% | estimated ± 7.7 pp, medium confidence |
| Vibe Code Bench | 54.1% | estimated ± 8.1 pp, medium confidence |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| Claw-Eval | 70.8% | estimated ± 5.7 pp, medium confidence |
| DeepPlanning | 49.4% | estimated ± 13.1 pp, low confidence |
| HMMT Feb 2025 | 98.4% | estimated ± 1.9 pp, low confidence |
| HMMT Feb 2026 | 89.8% | estimated ± 4.0 pp, high confidence |
| MCP Atlas | 78.7% | measured |
| MCP-Tasks | 77.1% | estimated ± 0.6 pp, low confidence |
| MMAnswerBench | 87.8% | estimated ± 1.3 pp, high confidence |
| MMLU-ProX | 85.9% | estimated ± 1.7 pp, medium confidence |
| MMLU-Redux | 93.5% | estimated ± 3.0 pp, medium confidence |
| NL2Repo | 49.2% | estimated ± 6.1 pp, medium confidence |
| NOVA-63 | 58.4% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 65.0% | estimated ± 2.6 pp, medium confidence |
| SuperGPQA | 77.2% | estimated ± 13.9 pp, low confidence |
| Toolathlon | 50.4% | estimated ± 3.5 pp, high confidence |
| LiveCodeBench Pro | 87.8% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 55.3% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.0% | estimated ± 3.4 pp, low confidence |
| ResearchClawBench | 19.0% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.8 pp, high confidence |
| FrontierCode 1.1 Extended | 57.7% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 51.1% | estimated ± 4.8 pp, low confidence |
| AIME 2025 | 98.1% | estimated ± 1.5 pp, low confidence |
| LiveCodeBench | 87.0% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 60.9% | estimated ± 4.9 pp, low confidence |
| MMMLU | 90.0% | estimated ± 1.1 pp, medium confidence |
| MATH-500 | 98.0% | estimated ± 3.1 pp, low confidence |