Artificial Analysis · Intelligence IndexBenchmarks, as Artificial Analysis ran them- 74%GPQA Diamond
- 8%Humanity's Last Exam
- 8%Terminal-Bench Hard
- 68%LiveCodeBench
- 66%AIME 2025
- 22%τ²-Bench
- 82%MMLU-Pro
- 40%IFBench
- 53%Long context reasoning
- Speed
- 123.7 tokens/s
- First answer
- 0.6 s
- thinking included
- Per 1M tokens
- $0.13 in · $1.15 out
- Context
- 262K tokens
LMArena164thof 416· 57th of 226 open models
Against list priceRating for the price
Qwen3 Next 80B A3B Instruct · 1,399 · $0.35 per 1M tokens ($0.10 in, $1.10 out) · 262K context
Qwen3 Next 80B A3B Instruct · 1,399 · $0.35 per 1M tokens ($0.10 in, $1.10 out) · 262K context
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 20 October 2026 · Artificial Analysis, read 20 October 2026
Qwen3 Next 80B A3B Instruct