Qwen3-Next-80B-A3B-Thinking qwen3-next-80b-a3b-thinking

qwen · qwen reasoning efficient

unranked — no quality signals yet

params
81.3B (A3B)
arch
moe
context
256k
license
apache-2.0 open weights
released
Sep 2025
reasoning
yes
downloads/30d
27.2k

# why ranked

Overall: provisional — score 71.3 ● low — a single signal; treat with caution

provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.

signalweightinput (0–100)
aa_intelligence 0.50
arena_elo 0.30
bench_composite 0.20 71.3

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
AIME 2025 0.9 / 1 LLM Stats
Arena-hard-v2 0.6 / 1 LLM Stats
Bfcl-v3 0.7 / 1 LLM Stats
Cfeval 2071.0 / 10000 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M blendtpsuptime
Alibabaunknown 128k $0.10$0.78$0.27
Googleunknown 256k $0.15$1.20$0.41

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

source aliases
llmstats
qwen3-next-80b-a3b-thinking
openrouter
qwen/qwen3-next-80b-a3b-thinking