modelbenchmark.io

Qwq 32B

Alibaba · qwq-32b

Compare

Qwen reasoning model for deliberate problem solving, math, and coding

Specification

most-agreed values

Context
24K
Max output
24K
Released
2025-03-05
Knowledge cutoff
2024-04
Retires
2025-11-13
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.66
Output
$1.00

Rate limits

Requests per minute
300

Quality

3 benchmarks · 2 sources

Composite
43rd
percentile of 344 scored models
Rank
198 / 344
±0.08 sd
Evidence
3 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding18th1/3 bench
reasoning58th1/4 bench
math62nd1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202559.2 ±6.3defaultEpoch AI2026-08-28
GPQA diamond65.3 ±2.8defaultEpoch AI2026-08-28
Aider polyglot20.9default · aider diffAider2025-03-06

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

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.15$0.40——131K131K—
nebius$0.15$0.45——33K33K—
nscale$0.18$0.20—————
hyperbolic$0.20$0.20——131K131K—
abacus$0.40$0.40——33K33K—
cloudflare$0.66$1.00——24K24K—
cloudflare-workers-ai · cf$0.66$1.00——24K24K—
fireworks_ai$0.90$0.90——131K131K—
together_ai$1.20$1.20——131K131K2025-11-13

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-13together_aiInput$1.20
2026-09-24together_aiInput$1.20
2026-09-13together_aiOutput$1.20
2026-09-24together_aiOutput$1.20

More from Alibaba

most-hosted first