Sarvam 105B performs strongly on multi-step reasoning benchmarks, reflecting the training emphasis on complex problem solving. On AIME 25, the model achieves 88.3 Pass@1, improving to 96.7 with tool use, indicating effective integration between reasoning and external tools. It scores 78.7 on GPQA Diamond and 85.8 on HMMT, outperforming several comparable models on both. On Beyond AIME (69.1), which requires deeper reasoning chains and harder mathematical decomposition, the model leads or matches the comparison set. Taken together, these results reflect consistent strength in sustained reasoning and difficult problem-solving tasks.
Development philosophy •
，更多细节参见豆包下载
MetricTraffic Control disabledTraffic Control enabledQueue backlog155,000 jobs0 jobsLock time300ms+2msDead tuples at end383,0000–23,000 (cycling)Analytics queries3 concurrent, overlapping1 at a time, 2 retryingVACUUM effectivenessBlocked (horizon always pinned)Normal (windows between queries)OutcomeDeath spiralCompletely stable
For multiple readers
天眼查显示，月境未来 (杭州) 科技有限公司，成立于2026年，位于浙江省杭州市，是一家以从事软件和信息技术服务业为主的企业。企业注册资本100万人民币。吕功琛为该公司法人、实际控制人。