Qwen3 Next 80B A3B Instruct
Qwen · released Sep 11, 2025
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Specification
- Context window
- 262K
- Max output
- 16K
- Knowledge cutoff
- Sep 30, 2025
- Parameters
- 81.3B
- Licence
- apache-2.0
- Serving providers
- 5
- Moderated
- No
- Uptime
- 100.0%
Intelligence
13.8
46th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
102 t/s
Median across providers
Latency
492ms
Time to first token
Cost per task
$0.03
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- MMLU-Pro81.9%
- GPQA Diamond73.8%
- LiveCodeBench68.4%
- AIME 202566.3%
- AA-LCR (long context)52.0%
- IFBench39.7%
- SciCode30.7%
- τ²-bench (Telecom)21.6%
- Humanity's Last Exam7.6%
- Terminal-Bench Hard7.6%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 81.9% |
| GPQA Diamond | 73.8% |
| LiveCodeBench | 68.4% |
| AIME 2025 | 66.3% |
| AA-LCR (long context) | 52.0% |
| IFBench | 39.7% |
| SciCode | 30.7% |
| τ²-bench (Telecom) | 21.6% |
| Humanity's Last Exam | 7.6% |
| Terminal-Bench Hard | 7.6% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Mistral Medium 3.1Mistral AI14.7
- Solar Pro 3Upstage14.5
- Llama 4 MaverickMeta14.5
- 14.4
- Ling-2.6-flashInclusionAI14.2
- Gemini 2.5 FlashGoogle14.2
- Qwen3 Next 80B A3B InstructQwen13.8
- 13.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Mistral Medium 3.1 | 14.7 |
| Solar Pro 3 | 14.5 |
| Llama 4 Maverick | 14.5 |
| Qwen3 VL 235B A22B Instruct | 14.4 |
| Ling-2.6-flash | 14.2 |
| Gemini 2.5 Flash | 14.2 |
| Qwen3 Next 80B A3B Instruct | 13.8 |
| Qwen3 Coder 30B A3B Instruct | 13.6 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.09
- Output / 1M tokens
- $1.1
- Cached input / 1M
- Not offered
- Blended 3:1
- $0.343
One task, estimated
$0.03
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).