Other · model
Beam 1.0 501B-A23B NVFP4 benchmark scores
As of 2026-10-29, Beam 1.0 501B-A23B NVFP4 (Other) has measured scores on 19 benchmarks and estimated scores on 99 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 88.9% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 33.3% | estimated ± 3.8 pp, high confidence |
| AA-SciCode | 46.5% | estimated ± 3.0 pp, high confidence |
| AIME26 | 97.5% | measured |
| CritPt | 15.4% | measured |
| GDPval-AA | 37.9% | estimated ± 7.7 pp, medium confidence |
| GPQA Diamond | 89.3% | measured |
| HLE | 42.2% | estimated ± 6.6 pp, medium confidence |
| IFBench | 79.2% | measured |
| AA-LCR | 78.7% | measured |
| LiveCodeBench v6 | 91.7% | estimated ± 2.7 pp, high confidence |
| SciCode | 46.9% | measured |
| Terminal-Bench 2.1 | 78.4% | measured |
| BrowseComp | 75.6% | measured |
| HLE w/ tools | 51.1% | measured |
| IFEval | 94.5% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 67.2% | measured |
| VITA-Bench | 43.2% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 97.0% | estimated ± 3.1 pp, high confidence |
| AA Coding Index | 67.7% | estimated ± 2.5 pp, high confidence |
| APEX-Agents | 34.3% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 21.7% | estimated ± 4.2 pp, high confidence |
| BioMysteryBench (human-difficult) | 46.7% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 81.1% | measured |
| SWE-bench Verified | 80.7% | measured |
| AutomationBench | 25.8% | estimated ± 10.5 pp, low confidence |
| BFCL v4 | 76.1% | estimated ± 4.7 pp, low confidence |
| CyberGym | 65.3% | estimated ± 7.3 pp, medium confidence |
| JobBench | 51.1% | estimated ± 6.4 pp, medium confidence |
| SWE-bench Pro | 65.6% | measured |
| τ³-bench results | 35.4% | measured |
| WideResearch | 75.6% | estimated ± 3.5 pp, high confidence |
| AA Agentic Index | 4.9% | estimated ± 5.9 pp, medium confidence |
| MMLU-Pro | 85.4% | estimated ± 2.5 pp, medium confidence |
| AA-IFBench | 80.3% | estimated ± 7.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 24.1% | estimated ± 6.1 pp, medium confidence |
| GPQA | 89.2% | estimated ± 1.2 pp, high confidence |
| AA-Omniscience Accuracy | 31.8% | estimated ± 8.1 pp, medium confidence |
| MATH-500 | 98.0% | estimated ± 3.1 pp, low confidence |
| MMMLU | 90.3% | estimated ± 0.7 pp, low confidence |
| AA MMLU-Pro | 88.4% | estimated ± 1.5 pp, low confidence |
| AIME 2025 | 97.8% | estimated ± 1.5 pp, low confidence |
| Gert Labs | 56.4% | estimated ± 7.4 pp, medium confidence |
| AA EnterpriseOps-Gym | 40.4% | estimated ± 3.3 pp, low confidence |
| AA Harvey LAB v1.0 | 88.1% | estimated ± 1.7 pp, medium confidence |
| AA Tau3 Banking | 32.2% | estimated ± 3.9 pp, high confidence |
| AA Terminal-Bench 2.1 | 79.7% | estimated ± 6.8 pp, medium confidence |
| ApprenticeBench | 12.5% | estimated ± 10.1 pp, low confidence |
| ARC-AGI-1 | 87.9% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 52.9% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 58.3% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 64.1% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 12.3% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 27.5% | estimated ± 2.7 pp, medium confidence |
| FrontierMath v2 (Tiers 1-3) | 49.9% | estimated ± 8.8 pp, medium confidence |
| FrontierSWE v2 | 25.1% | estimated ± 9.0 pp, medium confidence |
| MazeBench | 0.0% | estimated ± 6.1 pp, low confidence |
| OSWorld-Verified | 68.1% | estimated ± 5.8 pp, medium confidence |
| Vals GPQA Diamond | 88.5% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 85.6% | estimated ± 0.8 pp, medium confidence |
| Vals MMLU-Pro | 86.2% | estimated ± 1.6 pp, high confidence |
| Vals SWE-bench | 72.7% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 66.5% | estimated ± 7.4 pp, medium confidence |
| AA AutomationBench | 44.7% | estimated ± 11.6 pp, low confidence |
| CWE-Bench-AA | 52.2% | estimated ± 5.2 pp, medium confidence |
| AA Cyber Index | 34.3% | estimated ± 12.8 pp, low confidence |
| DeepsecBench-AA | 9.7% | estimated ± 6.0 pp, low confidence |
| GDP.pdf | 9.8% | estimated ± 4.9 pp, low confidence |
| AA ITBench | 43.8% | estimated ± 4.1 pp, high confidence |
| AA Terminal-Bench 4.0 | 16.1% | estimated ± 11.6 pp, low confidence |
| Bug Hunt Bench | 14.8% | estimated ± 9.4 pp, low confidence |
| CursorBench 4.0 | 39.8% | estimated ± 3.6 pp, high confidence |
| DeepSWE | 42.7% | measured |
| FrontierCode 2.0 | 22.4% | estimated ± 7.1 pp, low confidence |
| HLE w/o tools | 34.8% | measured |
| OSWorld 2.1 | 54.6% | estimated ± 8.3 pp, low confidence |
| PostTrainBench v1.1 | 16.7% | estimated ± 4.5 pp, medium confidence |
| SWE Multilingual | 77.5% | measured |
| Toolathlon-Verified | 66.9% | estimated ± 5.7 pp, medium confidence |
| Vibe Code Bench | 52.8% | estimated ± 8.1 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.6 pp, high confidence |
| Hermes Bench | 63.9% | estimated ± 4.8 pp, low confidence |
| Hermes Index | 26.4% | estimated ± 10.0 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 9.2 pp, low confidence |
| Claw-Eval | 70.9% | estimated ± 6.3 pp, low confidence |
| DeepPlanning | 50.3% | estimated ± 13.1 pp, low confidence |
| HMMT Feb 2025 | 98.0% | estimated ± 1.9 pp, low confidence |
| HMMT Feb 2026 | 92.2% | estimated ± 4.0 pp, high confidence |
| HMMT Nov 2025 | 95.6% | estimated ± 3.2 pp, high confidence |
| INCLUDE | 85.7% | estimated ± 2.0 pp, medium confidence |
| MCP Atlas | 80.5% | measured |
| MMAnswerBench | 87.2% | estimated ± 1.3 pp, high confidence |
| MMLU-ProX | 85.7% | estimated ± 1.3 pp, high confidence |
| MMLU-Redux | 92.5% | estimated ± 2.8 pp, high confidence |
| NL2Repo | 53.7% | estimated ± 6.1 pp, medium confidence |
| QwenClawBench | 66.3% | estimated ± 2.6 pp, medium confidence |
| SuperGPQA | 75.3% | estimated ± 13.9 pp, low confidence |
| Toolathlon | 45.1% | estimated ± 4.2 pp, high confidence |
| HealthBench Hard | 31.4% | estimated ± 8.6 pp, low confidence |
| LiveCodeBench Pro | 87.9% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 51.8% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 86.6% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 83.5% | estimated ± 2.3 pp, medium confidence |
| ResearchClawBench | 19.2% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, medium confidence |
| BioMysteryBench (human-solvable) | 87.8% | estimated ± 0.6 pp, medium confidence |
| DRACO | 81.1% | estimated ± 4.5 pp, medium confidence |
| FrontierCode 1.1 Extended | 57.7% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 48.8% | estimated ± 4.8 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, high confidence |
| LiveCodeBench | 79.7% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 23.0% | estimated ± 13.0 pp, low confidence |
| OpenHarmony Bench | 60.9% | estimated ± 4.9 pp, low confidence |
| IMOAnswerBench | 75.3% | estimated ± 10.7 pp, low confidence |
| MRCRv2 | 85.6% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.4% | estimated ± 2.6 pp, low confidence |
| PinchBench | 90.0% | estimated ± 3.6 pp, medium confidence |
| SWE-Atlas Codebase QnA | 31.4% | measured |