Compare / head-to-head
Qwen3-Next 80B-A3B InstructvsQwen3-Next 80B-A3B Thinking
Qwen3-Next 80B-A3B Thinking leads 11 of 13 shared benchmarks. Both list the same combined token price. Both offer a 262K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 11
Qwen3-Next 80B-A3B Thinking leads
Cheaper per token
Tie
list price, input + output
Larger context
Tie
both 262K tokens
Providers
Qwen
same provider
Qwen3-Next 80B-A3B Instruct
Qwen · released 2025-09-11
text
Qwen3-Next 80B-A3B Thinking
Qwen · released 2025-09-11
text
Quality
Benchmark matrix
13 shared · 3 only Qwen3-Next 80B-A3B Instruct · 3 only Qwen3-Next 80B-A3B Thinking| Benchmark | Qwen3-Next 80B-A3B Instruct | Qwen3-Next 80B-A3B Thinking | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 13 | ||||
| MMLU-Pro | 80.6% ↗ | 82.7% ↗ | -2.1 pt | Qwen3-Next 80B-A3B Thinking |
| LMArena Elo | 1399 ↗ | 1369.4 ↗ | +29.6 | Qwen3-Next 80B-A3B Instruct |
| AIME25 | 69.5% ↗ | 87.8% ↗ | -18.3 pt | Qwen3-Next 80B-A3B Thinking |
| Arena-Hard v2 | 82.7% ↗ | 62.3% ↗ | +20.4 pt | Qwen3-Next 80B-A3B Instruct |
| BFCL-v3 | 70.3% ↗ | 72% ↗ | -1.7 pt | Qwen3-Next 80B-A3B Thinking |
| GPQA | 72.9% ↗ | 77.2% ↗ | -4.3 pt | Qwen3-Next 80B-A3B Thinking |
| HMMT25 | 54.1% ↗ | 73.9% ↗ | -19.8 pt | Qwen3-Next 80B-A3B Thinking |
| IFEval | 87.6% ↗ | 88.9% ↗ | -1.3 pt | Qwen3-Next 80B-A3B Thinking |
| LiveCodeBench v6 (25.02-25.05) | 56.6% ↗ | 68.7% ↗ | -12.1 pt | Qwen3-Next 80B-A3B Thinking |
| MMLU-Redux | 90.9% ↗ | 92.5% ↗ | -1.6 pt | Qwen3-Next 80B-A3B Thinking |
| SuperGPQA | 58.8% ↗ | 60.8% ↗ | -2 pt | Qwen3-Next 80B-A3B Thinking |
| TAU2-Airline | 45.5% ↗ | 60.5% ↗ | -15 pt | Qwen3-Next 80B-A3B Thinking |
| TAU2-Retail | 57.3% ↗ | 67.8% ↗ | -10.5 pt | Qwen3-Next 80B-A3B Thinking |
| Only Qwen3-Next 80B-A3B Instruct reports · 3 | ||||
| Aider-Polyglot | 49.8% ↗ | not reported | — | — |
| LiveBench 20241125 | 75.8% ↗ | not reported | — | — |
| MultiPL-E | 87.8% ↗ | not reported | — | — |
| Only Qwen3-Next 80B-A3B Thinking reports · 3 | ||||
| LiveBench 241125 | not reported | 76.6% ↗ | — | — |
| OJBench | not reported | 29.7% ↗ | — | — |
| TAU2-Telecom | not reported | 43.9% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Qwen3-Next 80B-A3B Instruct minus Qwen3-Next 80B-A3B Thinking in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Qwen3-Next 80B-A3B Instruct | Qwen3-Next 80B-A3B Thinking | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.15 ↗ | $0.15 ↗ | Tie |
| Output price / 1M | $1.2 ↗ | $1.2 ↗ | Tie |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.35 | $1.35 | Tie |
| Modalities | text | text | Tie |
| Released | 2025-09-11 | 2025-09-11 | — |
| Cited benchmark scores | 16 | 16 | — |
Reliability
Qwen status
Live from /statusMore matchups
Qwen3-Next 80B-A3B Instruct vs …
Models sharing the most benchmarksMore matchups
Qwen3-Next 80B-A3B Thinking vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3-Next 80B-A3B Instruct and Qwen3-Next 80B-A3B Thinking on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.