Other · model
Sarvam 30B benchmark scores
As of 2026-11-22, Sarvam 30B (Other) has measured scores on 14 benchmarks and estimated scores on 61 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 63.3% | measured |
| AA-HLE | 7.5% | measured |
| AA-SciCode | 23.9% | estimated ± 3.8 pp, medium confidence |
| AIME26 | 86.2% | estimated ± 1.6 pp, medium confidence |
| Artificial Analysis Intelligence Index | 9.7% | estimated ± 3.2 pp, medium confidence |
| CritPt | 0.3% | measured |
| GDPval-AA | 18.2% | estimated ± 7.8 pp, low confidence |
| GPQA Diamond | 66.5% | measured |
| HLE | 7.5% | estimated ± 6.8 pp, medium confidence |
| IFBench | 53.6% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 0.0% | measured |
| AA-Omniscience Accuracy | 16.4% | estimated ± 2.4 pp, high confidence |
| SciCode | 23.4% | estimated ± 3.6 pp, medium confidence |
| BrowseComp | 35.5% | measured |
| HLE w/ tools | 34.7% | estimated ± 5.6 pp, low confidence |
| IFEval | 80.3% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.2% | estimated ± 5.5 pp, low confidence |
| VITA-Bench | 6.1% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 34.5% | measured |
| AA Coding Index | 23.4% | estimated ± 5.3 pp, medium confidence |
| APEX-Agents-AA | 6.9% | estimated ± 4.4 pp, medium confidence |
| BioMysteryBench (human-difficult) | 6.5% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 74.5% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 34.0% | measured |
| BFCL v4 | 32.1% | estimated ± 8.5 pp, low confidence |
| CyberGym | 23.2% | estimated ± 7.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 10.7 pp, low confidence |
| SWE-bench Pro | 7.5% | estimated ± 4.5 pp, medium confidence |
| WideResearch | 48.2% | estimated ± 3.5 pp, medium confidence |
| AA Agentic Index | 7.6% | estimated ± 8.2 pp, low confidence |
| MMLU-Pro | 80.0% | measured |
| AA-IFBench | 26.5% | measured |
| AIME 2024 | 77.6% | estimated ± 7.1 pp, medium confidence |
| BBH | 90.0% | estimated ± 2.4 pp, low confidence |
| GPQA | 66.3% | estimated ± 1.2 pp, high confidence |
| MMLU | 85.1% | measured |
| Vals GPQA Diamond | 62.4% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 47.7% | estimated ± 10.0 pp, low confidence |
| Vals MMLU-Pro | 72.0% | estimated ± 2.4 pp, high confidence |
| MATH-500 | 97.0% | measured |
| MMMLU | 85.4% | estimated ± 0.7 pp, medium confidence |
| AIME 2025 | 82.3% | estimated ± 2.0 pp, high confidence |
| AA MMLU-Pro | 85.7% | estimated ± 1.3 pp, medium confidence |
| Gert Labs | 28.8% | estimated ± 11.1 pp, low confidence |
| AA Harvey LAB v1.0 | 78.9% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-1 | 75.0% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 31.1% | estimated ± 14.4 pp, low confidence |
| MazeBench | 0.0% | estimated ± 6.4 pp, low confidence |
| OSWorld-Verified | 49.6% | estimated ± 5.7 pp, low confidence |
| Vals SWE-bench | 14.3% | estimated ± 6.6 pp, low confidence |
| CWE-Bench-AA | 26.2% | estimated ± 6.4 pp, low confidence |
| AA Cyber Index | 19.1% | estimated ± 13.5 pp, low confidence |
| AA ITBench | 23.3% | estimated ± 4.1 pp, medium confidence |
| HLE w/o tools | 8.9% | estimated ± 4.3 pp, medium confidence |
| Toolathlon-Verified | 19.9% | estimated ± 7.4 pp, low confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| C-Eval | 91.1% | estimated ± 1.1 pp, medium confidence |
| Claw-Eval | 62.7% | estimated ± 6.4 pp, low confidence |
| HMMT Feb 2025 | 73.3% | measured |
| HMMT Feb 2026 | 62.3% | estimated ± 3.4 pp, medium confidence |
| HMMT Nov 2025 | 74.2% | measured |
| MCP Atlas | 48.8% | estimated ± 10.3 pp, low confidence |
| MMLU-Redux | 90.4% | estimated ± 0.6 pp, high confidence |
| SuperGPQA | 61.6% | estimated ± 12.4 pp, low confidence |
| Toolathlon | 16.0% | estimated ± 4.2 pp, medium confidence |
| HealthBench Hard | 3.5% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 77.3% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 58.9% | estimated ± 2.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| SimpleQA | 20.2% | estimated ± 7.8 pp, medium confidence |
| LiveCodeBench | 43.6% | estimated ± 14.6 pp, low confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 10.7 pp, low confidence |
| PinchBench | 85.1% | estimated ± 3.6 pp, low confidence |