benchgap
Other · model

Sarvam 105B benchmark scores

As of 2026-11-22, Sarvam 105B (Other) has measured scores on 16 benchmarks and estimated scores on 64 more.

BenchmarkScoreSource
AA-GPQA Diamond73.8%measured
AA-HLE11.0%measured
AA-SciCode30.5%estimated ± 3.8 pp, high confidence
AIME2691.0%estimated ± 1.0 pp, low confidence
Artificial Analysis Intelligence Index12.2%estimated ± 3.2 pp, medium confidence
CritPt0.0%measured
GDPval-AA19.4%estimated ± 7.8 pp, medium confidence
GPQA Diamond78.7%measured
HLE13.7%estimated ± 6.8 pp, medium confidence
IFBench53.8%estimated ± 6.6 pp, low confidence
AA-LCR0.0%measured
AA-Omniscience Accuracy28.5%estimated ± 2.4 pp, high confidence
SciCode29.9%estimated ± 3.6 pp, high confidence
BrowseComp49.5%measured
HLE w/ tools36.4%estimated ± 5.6 pp, medium confidence
IFEval84.8%measured
LongBench v251.2%estimated ± 5.5 pp, low confidence
VITA-Bench18.6%estimated ± 6.7 pp, low confidence
τ²-bench results46.8%measured
AA Coding Index23.9%estimated ± 5.3 pp, medium confidence
APEX-Agents-AA8.1%estimated ± 4.4 pp, medium confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
DeepSearchQA75.2%estimated ± 6.8 pp, low confidence
SWE-bench Verified45.0%measured
BFCL v441.2%estimated ± 8.5 pp, low confidence
CyberGym35.4%estimated ± 7.3 pp, low confidence
JobBench2.1%estimated ± 10.7 pp, low confidence
SWE-bench Pro19.7%estimated ± 4.5 pp, medium confidence
WideResearch59.8%estimated ± 3.5 pp, medium confidence
AA Agentic Index12.6%estimated ± 8.2 pp, medium confidence
MMLU-Pro81.7%measured
AA-IFBench34.4%measured
AIME 202491.0%estimated ± 2.6 pp, high confidence
BBH96.3%estimated ± 2.4 pp, low confidence
GPQA78.6%estimated ± 1.2 pp, high confidence
MMLU90.6%measured
Vals GPQA Diamond78.4%estimated ± 2.1 pp, medium confidence
Vals LiveCodeBench49.9%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro80.1%estimated ± 1.6 pp, medium confidence
MATH-50098.6%measured
MMMLU83.3%estimated ± 0.7 pp, medium confidence
AIME 202588.3%measured
AA MMLU-Pro85.7%estimated ± 1.3 pp, medium confidence
Gert Labs28.9%estimated ± 11.1 pp, low confidence
AA Harvey LAB v1.082.7%estimated ± 9.8 pp, low confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
FrontierMath v2 (Tiers 1-3)26.7%estimated ± 11.2 pp, low confidence
MazeBench0.0%estimated ± 6.4 pp, low confidence
OSWorld-Verified51.2%estimated ± 5.7 pp, low confidence
Vals SWE-bench29.1%estimated ± 6.6 pp, low confidence
CWE-Bench-AA34.7%estimated ± 6.4 pp, medium confidence
AA Cyber Index25.7%estimated ± 13.5 pp, low confidence
AA ITBench31.0%estimated ± 4.1 pp, medium confidence
HLE w/o tools12.7%estimated ± 4.3 pp, high confidence
Toolathlon-Verified34.0%estimated ± 7.4 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
C-Eval90.8%estimated ± 1.1 pp, low confidence
Claw-Eval62.7%estimated ± 6.4 pp, low confidence
HMMT Feb 202585.8%measured
HMMT Feb 202681.3%estimated ± 1.2 pp, low confidence
HMMT Nov 202585.8%measured
MCP Atlas48.8%estimated ± 10.3 pp, low confidence
MMAnswerBench77.7%estimated ± 2.0 pp, low confidence
MMLU-Redux91.4%estimated ± 0.6 pp, high confidence
SuperGPQA63.9%estimated ± 12.4 pp, low confidence
Toolathlon24.4%estimated ± 4.2 pp, medium confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)82.7%estimated ± 3.4 pp, medium confidence
React Native Evals63.9%estimated ± 2.7 pp, low confidence
ResearchClawBench12.3%estimated ± 2.3 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
SimpleQA25.5%estimated ± 7.8 pp, medium confidence
LiveCodeBench53.9%estimated ± 14.6 pp, low confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
BioBasicsBench33.9%estimated ± 10.7 pp, low confidence
LifeVal16.3%estimated ± 1.6 pp, low confidence
PinchBench87.6%estimated ± 3.6 pp, medium confidence