Sarvam 30B (High)
Sarvam开源权重Apache 2.0 · 商用许可
描述
Sarvam-30B is an open-source 30B-parameter Mixture-of-Experts reasoning model from Sarvam AI trained from scratch and optimized for Indian languages, coding, and conversational workloads. It uses 128 sparse experts with 2.4B active parameters per token, Grouped Query Attention, and was pre-trained on 16 trillion tokens spanning code, mathematics, multilingual, and web data.
发布日期
2026-03-06
参数规模
30.0B
上下文长度
66K
支持模态
text
能力雷达图
70
general
60
coding
80
reasoning
60
science估算
40
agents
0
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
暂无排名数据
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
85.1%自报
Arena-Hard v2
49.0%自报
Language
MMLU-Pro
80.0%自报
Math
MATH-500
97.0%自报
AIME 2025
96.7%自报
HMMT25
74.2%自报
HMMT 2025
73.3%自报
Beyond AIME
58.3%自报
Reasoning
MBPP
0.93 / 100自报
HumanEvalOpenAI (2021)
92.1%自报
LiveCodeBench v6
70.0%自报
GPQANYU + Cohere + Anthropic (2023)
66.5%自报
BrowseCompOpenAI (2025)
35.5%自报
SWE-Bench Verified
34.0%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Language80
Legal80
Math80
Finance80
Healthcare80
Physics70
Reasoning70
General70
Biology70
Chemistry70
Code60
Creativity50
Writing50
Search40
Agents40
Frontend Development30
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据