跳轉到主要內容
AITier

Sarvam 105B (high)

Sarvam開源權重Apache 2.0 · 商用許可

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.

發布日期
2026-03-06
參數規模
105.0B
上下文長度
131K
支援模態
text

能力雷達圖

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

排行榜排名

領域#排名分數來源
程式碼能力榜643
1.0
AA
通用能力榜530
25.0
AA
科學能力314
45.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)84.8%自報

General

MMLU90.6%自報
Arena-Hard v271.0%自報

Language

MMLU-Pro81.7%自報

Math

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

Reasoning

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

AA 評測指數

(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 分類評分

(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

定價

輸入價格$0.042 / 1M tokens
輸出價格$0.17 / 1M tokens
混合價格(3:1)$0.074 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: Sarvam最貴: NanoGPT
供應商輸入輸出
1Sarvam主要
$0.042
$0.17
2NanoGPT
$0.054
$0.2124

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM StatsArtificial Analysis