modelbenchmark.io

qwen2-72b-instruct

Alibaba · qwen2-72b-instruct

Compare

Specification

most-agreed values

Context
33K
Max output
33K
Released
Knowledge cutoff
Retires
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$0.90
Output
$0.90

Quality

2 benchmarks · 1 source

Composite
26th
percentile of 334 scored models
Rank
248 / 334
±0.06 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
one configuration only
reasoning18th1/4 bench
math35th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 539.1 ±1.0defaultEpoch AI2025-01-27
GPQA diamond40.8 ±2.6defaultEpoch AI2025-01-27

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

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$0.90$0.9033K33K
together_ai$0.90$0.90

More from Alibaba

most-hosted first