跳转到主要内容

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

12
general
26
coding
74
reasoning
45
science
50
agents
0
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜85
43.0
LS
代码能力榜562
1.0
AA
通用能力榜437
29.0
AA
科学能力283
46.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

BrowseCompOpenAI (2025)49.5%自报

Biology

GPQANYU + Cohere + Anthropic (2023)78.7%自报

Code

SWE-Bench Verified45.0%自报

Creativity

Arena-Hard v271.0%自报

Finance

MMLU90.6%自报
MMLU-Pro81.7%自报

General

IFEvalGoogle Research (2023)84.8%自报
LiveCodeBench v671.7%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
Humanity's Last Exam11.2%自报

AA 评测指数

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
11.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Ifbench(Google Research (2023))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0
Lcr(Artificial Analysis)
0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))
Legal
90
Language
90
Finance
90
Healthcare
90
Math
80
Physics
80
Structured Output
80
Instruction Following
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
$0.045
$0.177

比较该模型在不同 API 供应商之间的定价。

外部链接