Pass IndexThe State of AISign in

Qwen 2.5 7B Instruct Turbo

An instruction-tuned causal language model of 7.61B parameters in the Qwen2.5 series, with improved coding, mathematics, long-text generation, structured data understanding and JSON output across 29+ languages.

text → text · made by Alibaba

$0.3$0.3per Mtok in / out
Together AI

Sold by 1 way

SellerLaneRate
Together AI aggregatorstandard$0.3per Mtok in$0.3per Mtok outdocs.together.ai · read 2026-08-24

Measured 1 standing

PlaceBoardMetricScore
4thof 25AgentBench Leaderboard (new)Success Rate (pass@1) AVG62

About

Qwen 2.5 7B Instruct Turbo — a text model from Alibaba, sold by one company from $0.3 in and $0.3 out per million tokens, placed 4th of 25 on AgentBench Leaderboard (new).

It takes text and returns text, with a context window of 32,768 tokens. It was published in September 2024. Its sellers say it can call a tool. The catalogue files it under agents. Only Together AI sells it, at $0.3 in and $0.3 out per million tokens. It stands 4th of 25 on AgentBench Leaderboard (new).

Every current figure

Maker
Alibaba
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Published
September 2024
Parameters
7 billion · read from its own name
Sellers
1
Maker's own price
not read
Price
$0.3 in and $0.3 out per million tokens — Together AI
Boards
1
Best place
4th of 25 — AgentBench Leaderboard (new)

Known as 2 names

AgentRL w/ Qwen2.5-7B-InstructQwen/Qwen2.5-7B-Instruct-Turbo