Qwen

Qwen3 Next 80B A3B Thinking

by Qwentext->text2 endpoints
Neura Intelligence Index
65.8/ 100
Rank
#112
Confidence
low
Benchmarks
3(8% coverage)

Overview

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
32.8K tokens
Knowledge Cutoff
2025-09-30
Tokenizer
Qwen3
Uptime (24h)
10000.0%
Parameters
80000000000B
License
apache_2_0Open Weights
Country
🇨🇳CN
Release Date
September 10, 20251y

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

math

BenchmarkScoreSource
AIME 2025
87.8
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
77.2
verified

agent

BenchmarkScoreSource
TAU-Bench Retail
69.6
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.15
Output$1.20
Added
September 11, 2025
Last synced 9/16/2026