跳转到主要内容
AITier

Sarvam 105B (high)

Sarvam开源权重Apache 2.0 · 商用许可

描述

Sarvam-105B is Sarvam AI's flagship open-source Mixture-of-Experts reasoning model built for complex reasoning, coding, and agentic workflows. It uses 128 sparse experts with Multi-head Latent Attention for efficient long-context inference and was pre-trained on 12 trillion tokens spanning code, mathematics, multilingual, and web data.

发布日期
2026-03-06
参数规模
105.0B
上下文长度
131K
支持模态
text

能力雷达图

9
general
50
coding
74
reasoning
54
science
50
agents
0
multimodal

排行榜排名

领域#排名分数来源
代码能力榜645
1.0
AA
通用能力榜532
25.0
AA
科学能力315
45.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)84.8%自报

General

MMLU90.6%自报
Arena-Hard v271.0%自报

Language

MMLU-Pro81.7%自报

Math

MATH-50098.6%自报
AIME 202596.7%自报
HMMT2585.8%自报
HMMT 202585.8%自报
Beyond AIME69.1%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)78.7%自报
LiveCodeBench v671.7%自报
BrowseCompOpenAI (2025)49.5%自报
SWE-Bench Verified45.0%自报
Humanity's Last Exam11.2%自报

AA 评测指数

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
73.8
Tau2(Sierra + U Toronto + Vector Institute (2025))
46.8
Ifbench(Google Research (2023))
34.4
Hle(Center for AI Safety + Scale AI (2025))
11.0
Intelligence Index(Artificial Analysis)
8.8
Terminalbench Hard(Stanford × Laude Institute (2026))
1.5
Lcr(Artificial Analysis)
0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))
Language
90
Legal
90
Finance
90
Healthcare
90
Chat
80
Instruction Following
80
Math
80
Physics
80
Structured Output
80
Biology
80
Chemistry
80
Reasoning
70
General
70
Creativity
70
Writing
70
Search
50
Frontend Development
50
Agents
50
Code
50
Vision
10

定价

输入价格$0.042 / 1M tokens
输出价格$0.17 / 1M tokens
混合价格(3:1)$0.074 / 1M tokens

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

2 个供应商

最便宜: Sarvam最贵: NanoGPT
供应商输入输出
1Sarvam主要
$0.042
$0.17
2NanoGPT
$0.054
$0.2124

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM StatsArtificial Analysis