modelbenchmark.io

Qwen2.5 7B Instruct

Alibaba · qwen2-5-7b-instruct

Compare

Qwen instruction model for multilingual chat, reasoning, and tool use

Specification

alibaba listing

Context
131K
Max output
8K
Released
2024-09
Knowledge cutoff
2024-04
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · alibaba list price

Input
$0.175
Output
$0.70

Quality

3 benchmarks · 1 source

Composite
12th
percentile of 334 scored models
Rank
293 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning16th2/4 bench
math6th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Chess Puzzles0.0 ±0.0defaultEpoch AI2026-08-30
GPQA diamond35.5 ±2.3defaultEpoch AI2026-08-30
OTIS Mock AIME 2024-20252.5 ±0.9defaultEpoch AI2026-08-30

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibabavendor$0.175$0.70131K8K
deepinfra$0.04$0.1033K33K
siliconflow$0.05$0.0533K4K
siliconflow-cn$0.05$0.0533K4K
novita$0.07$0.0732K8K
novita-ai$0.07$0.0732K32K
alibaba-cn$0.072$0.144131K8K
fireworks_ai$0.20$0.2033K33K

Other listings of this model

same model, different key

More from Alibaba

most-hosted first