Qwen3 32B qwen3-32b

qwen · qwen hybrid-reasoning

unranked — no quality signals yet

params
32.8B
arch
dense
context
128k
license
apache-2.0 open weights
released
Apr 2025
reasoning
yes

# why ranked

Coding: #23 — score 36.4 ● low — a single signal; treat with caution

signalweightinput (0–100)
aa_coding 0.25
aider_polyglot 0.25 36.4
arena_elo_code 0.15
swe_bench_verified 0.35

missing signals are dropped and the remaining weights renormalized — never imputed.

full methodology

# trend

collecting history — trends appear after a few daily runs.

# benchmarks

benchmarkscoresourcedate
Aider Polyglot 40.0 Aider May 2025

# where to run

providerquantctx$/M in$/M out$/M blendtpsuptime
DeepInfrafp8 40k $0.08$0.28$0.13 99.9%
Nebiusfp8 40k $0.10$0.30$0.15 93.7%
Alibabaunknown 128k $0.10$0.42$0.18 99.7%
SiliconFlowfp8 128k $0.14$0.57$0.25 99.9%
Groqunknown 128k $0.29$0.59$0.36 99.8%

blended = (3·input + output) / 4 per 1M tokens · cheapest first

source aliases
aa
qwen3-32b
aider
Qwen3 32B
arena
Qwen3-32B
openrouter
qwen/qwen3-32b