Other · model
Ripple-65B Preview benchmark scores
As of 2026-11-04, Ripple-65B Preview (Other) has measured scores on 17 benchmarks and estimated scores on 85 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 84.1% | estimated ± 4.4 pp, high confidence |
| AA-HLE | 25.2% | estimated ± 3.8 pp, high confidence |
| AA-SciCode | 39.6% | estimated ± 3.0 pp, high confidence |
| AIME26 | 95.0% | measured |
| CritPt | 1.2% | estimated ± 3.4 pp, medium confidence |
| GDPval-AA | 33.9% | estimated ± 10.2 pp, low confidence |
| GPQA Diamond | 85.2% | measured |
| HLE | 24.5% | estimated ± 7.3 pp, medium confidence |
| IFBench | 79.2% | measured |
| AA-LCR | 75.0% | measured |
| LiveCodeBench v6 | 90.1% | estimated ± 2.7 pp, high confidence |
| SciCode | 39.4% | measured |
| Terminal-Bench 2.1 | 80.5% | measured |
| BrowseComp | 87.3% | estimated ± 7.0 pp, low confidence |
| HLE w/ tools | 46.4% | estimated ± 10.1 pp, low confidence |
| IFEval | 94.5% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 61.2% | estimated ± 5.8 pp, low confidence |
| VITA-Bench | 44.8% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 68.2% | estimated ± 2.5 pp, high confidence |
| APEX-Agents | 27.2% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 31.5% | estimated ± 5.5 pp, medium confidence |
| SWE-bench Verified | 76.5% | measured |
| AutomationBench | 36.4% | measured |
| BFCL v4 | 73.4% | estimated ± 4.7 pp, low confidence |
| CyberGym | 83.1% | estimated ± 4.6 pp, medium confidence |
| JobBench | 42.3% | estimated ± 6.4 pp, medium confidence |
| SWE-bench Pro | 61.4% | measured |
| τ³-bench results | 31.3% | measured |
| WideResearch | 70.9% | estimated ± 6.7 pp, low confidence |
| AA Agentic Index | 4.9% | estimated ± 5.9 pp, medium confidence |
| MMLU-Pro | 84.2% | measured |
| AA-IFBench | 80.3% | estimated ± 7.4 pp, medium confidence |
| AIME 2024 | 97.1% | measured |
| Artificial Analysis Intelligence Index | 12.7% | estimated ± 2.1 pp, high confidence |
| BBH | 95.2% | estimated ± 2.4 pp, low confidence |
| GPQA | 85.1% | estimated ± 1.2 pp, high confidence |
| MMLU | 89.6% | measured |
| AA-Omniscience Accuracy | 25.8% | estimated ± 1.5 pp, high confidence |
| MATH-500 | 98.4% | estimated ± 1.2 pp, medium confidence |
| MMMLU | 87.8% | estimated ± 1.1 pp, medium confidence |
| AIME 2025 | 98.3% | measured |
| Gert Labs | 62.4% | estimated ± 8.2 pp, low confidence |
| AA Tau3 Banking | 44.6% | estimated ± 3.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 80.9% | estimated ± 6.8 pp, medium confidence |
| ARC-AGI-1 | 80.9% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 40.3% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 55.6% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 59.9% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 13.8% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 14.4% | estimated ± 2.7 pp, low confidence |
| FrontierMath v2 (Tier 4) | 18.6% | estimated ± 4.3 pp, medium confidence |
| FrontierMath v2 (Tiers 1-3) | 36.8% | estimated ± 8.8 pp, medium confidence |
| FrontierSWE v2 | 17.7% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 71.5% | estimated ± 9.4 pp, low confidence |
| Vals GPQA Diamond | 84.3% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 83.7% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 83.9% | estimated ± 1.6 pp, high confidence |
| Vals SWE-bench | 62.5% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 68.1% | estimated ± 7.4 pp, medium confidence |
| CWE-Bench-AA | 56.2% | estimated ± 6.0 pp, low confidence |
| AA Cyber Index | 32.8% | estimated ± 9.4 pp, medium confidence |
| DeepsecBench-AA | 0.0% | estimated ± 6.0 pp, low confidence |
| AA ITBench | 42.0% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 18.4% | estimated ± 11.6 pp, low confidence |
| Bug Hunt Bench | 15.1% | estimated ± 9.4 pp, low confidence |
| CursorBench 4.0 | 36.6% | estimated ± 3.6 pp, medium confidence |
| DeepSWE | 44.3% | measured |
| FrontierCode 2.0 | 20.7% | estimated ± 7.1 pp, low confidence |
| HLE w/o tools | 21.6% | estimated ± 4.3 pp, high confidence |
| PostTrainBench v1.1 | 17.7% | estimated ± 4.5 pp, medium confidence |
| Toolathlon-Verified | 63.6% | estimated ± 9.2 pp, medium confidence |
| Vibe Code Bench | 9.4% | estimated ± 8.1 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.6 pp, medium confidence |
| C-Eval | 90.2% | estimated ± 1.3 pp, medium confidence |
| Claw-Eval | 68.5% | estimated ± 6.3 pp, low confidence |
| DeepPlanning | 46.0% | estimated ± 13.1 pp, low confidence |
| HMMT Feb 2025 | 97.1% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 90.5% | measured |
| HMMT Nov 2025 | 94.8% | estimated ± 2.8 pp, high confidence |
| MCP Atlas | 71.7% | measured |
| MMAnswerBench | 82.8% | estimated ± 1.3 pp, high confidence |
| MMLU-Redux | 92.7% | estimated ± 0.6 pp, high confidence |
| NL2Repo | 48.7% | estimated ± 6.1 pp, medium confidence |
| QwenClawBench | 60.4% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 67.2% | estimated ± 12.1 pp, low confidence |
| Toolathlon | 49.1% | estimated ± 7.5 pp, medium confidence |
| LiveCodeBench Pro | 84.8% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 42.1% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 85.2% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 75.0% | estimated ± 2.3 pp, medium confidence |
| ResearchClawBench | 18.3% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 58.6% | estimated ± 3.6 pp, medium confidence |
| DRACO | 75.5% | estimated ± 4.5 pp, medium confidence |
| FrontierCode 1.1 Extended | 56.5% | estimated ± 3.0 pp, low confidence |
| SimpleQA | 38.1% | estimated ± 13.1 pp, low confidence |
| LiveCodeBench | 77.1% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench | 55.7% | estimated ± 4.9 pp, low confidence |
| IMOAnswerBench | 83.5% | estimated ± 5.6 pp, medium confidence |
| MRCRv2 | 84.2% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.2% | estimated ± 2.6 pp, low confidence |
| PinchBench | 91.7% | estimated ± 5.5 pp, low confidence |
| SWE-Atlas Codebase QnA | 35.5% | estimated ± 5.4 pp, low confidence |