by AlibabaRank #130Score 63.6
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...
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 20% | 13.3 | 2026-06-24T10:08:34.724Z |
Benchmarks benchmark | 62.7 | 30% | 18.8 | 2026-06-24T10:08:34.724Z |
Pricing pricing_tier | 99.2 | 15% | 14.9 | 2026-06-24T10:08:34.724Z |
Context Window context_window | 77.4 | 10% | 7.7 | 2026-06-24T10:08:34.724Z |
Recency recency | 80.8 | 15% | 12.1 | 2026-06-24T10:08:34.724Z |
Output Capacity output_capacity | 75.3 | 10% | 7.5 | 2026-06-24T10:08:34.724Z |
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |