Compare / head-to-head
Qwen3-Coder 30B-A3B InstructvsQwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct leads 2 of 2 shared benchmarks. Qwen3-Next 80B-A3B Instruct is 2x cheaper per token. Both offer a 262K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Qwen3-Next 80B-A3B Instruct leads
Cheaper per token
Qwen3-Next 80B-A3B Instruct
2x cheaper, input + output
Larger context
Tie
both 262K tokens
Providers
Qwen
same provider
Qwen3-Coder 30B-A3B Instruct
Qwen · released 2025-07-31
text
Qwen3-Next 80B-A3B Instruct
Qwen · released 2025-09-11
text
Quality
Benchmark matrix
2 shared · 11 only Qwen3-Coder 30B-A3B Instruct · 14 only Qwen3-Next 80B-A3B Instruct| Benchmark | Qwen3-Coder 30B-A3B Instruct | Qwen3-Next 80B-A3B Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| Aider-Polyglot | 33.3% ↗ | 49.8% ↗ | -16.5 pt | Qwen3-Next 80B-A3B Instruct |
| BFCL-v3 | 62.2% ↗ | 70.3% ↗ | -8.1 pt | Qwen3-Next 80B-A3B Instruct |
| Only Qwen3-Coder 30B-A3B Instruct reports · 11 | ||||
| Mind2Web | 51% ↗ | not reported | — | — |
| Multi-SWE-bench flash | 19.3% ↗ | not reported | — | — |
| Multi-SWE-bench mini | 19.5% ↗ | not reported | — | — |
| Spider2 | 21.4% ↗ | not reported | — | — |
| SWE-bench Live | 20.7% ↗ | not reported | — | — |
| SWE-bench Multilingual | 34.7% ↗ | not reported | — | — |
| SWE-bench Verified (w/ OpenHands, 500 turns) | 51.6% ↗ | not reported | — | — |
| TAU-Bench Airline | 48% ↗ | not reported | — | — |
| TAU-Bench Retail | 68.7% ↗ | not reported | — | — |
| Terminal-Bench | 31.3% ↗ | not reported | — | — |
| WebArena | 43.5% ↗ | not reported | — | — |
| Only Qwen3-Next 80B-A3B Instruct reports · 14 | ||||
| MMLU-Pro | not reported | 80.6% ↗ | — | — |
| LMArena Elo | not reported | 1399 ↗ | — | — |
| AIME25 | not reported | 69.5% ↗ | — | — |
| Arena-Hard v2 | not reported | 82.7% ↗ | — | — |
| GPQA | not reported | 72.9% ↗ | — | — |
| HMMT25 | not reported | 54.1% ↗ | — | — |
| IFEval | not reported | 87.6% ↗ | — | — |
| LiveBench 20241125 | not reported | 75.8% ↗ | — | — |
| LiveCodeBench v6 (25.02-25.05) | not reported | 56.6% ↗ | — | — |
| MMLU-Redux | not reported | 90.9% ↗ | — | — |
| MultiPL-E | not reported | 87.8% ↗ | — | — |
| SuperGPQA | not reported | 58.8% ↗ | — | — |
| TAU2-Airline | not reported | 45.5% ↗ | — | — |
| TAU2-Retail | not reported | 57.3% ↗ | — | — |
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-Coder 30B-A3B Instruct minus Qwen3-Next 80B-A3B Instruct 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-Coder 30B-A3B Instruct | Qwen3-Next 80B-A3B Instruct | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.45 ↗ | $0.15 ↗ | Qwen3-Next 80B-A3B Instruct |
| Output price / 1M | $2.25 ↗ | $1.2 ↗ | Qwen3-Next 80B-A3B Instruct |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2.7 | $1.35 | Qwen3-Next 80B-A3B Instruct |
| Modalities | text | text | Tie |
| Released | 2025-07-31 | 2025-09-11 | — |
| Cited benchmark scores | 13 | 16 | — |
Reliability
Qwen status
Live from /statusMore matchups
Qwen3-Coder 30B-A3B Instruct vs …
Models sharing the most benchmarksMore matchups
Qwen3-Next 80B-A3B Instruct vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3-Coder 30B-A3B Instruct and Qwen3-Next 80B-A3B Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.