Model comparison
Qwen3 Max vs Qwen3-Next 80B-A3B Instruct
Qwen3 Max is the stronger model overall, scoring 43.5 to 42.5 on the Noometry Index. Qwen3-Next 80B-A3B Instruct costs 2.7× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Qwen3 Max scores higher in 7 categories and Qwen3-Next 80B-A3B Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 30.1 to 22.0.
- The biggest single-benchmark swing is Fiction.LiveBench: 66.7% for Qwen3 Max and 55.6% for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct is cheaper at $0.50 / $2 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 131K.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen3 Max | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 43.5 | 42.5 |
| Released | 2025-09-23 | 2025-09 |
| Weights | Proprietary | Open |
| Context window | 262K | 131K |
| Max output | 66K | 33K |
| Input $ / M tokens | $1.20 | $0.50 |
| Output $ / M tokens | $6 | $2 |
| Results tracked | 33 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen3 Max: 42.4 (#93), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1456 | 1441 |
| ALE-Bench | 370.45 | — |
Agentic & Tool Use Not comparable
Qwen3 Max: —, Qwen3-Next 80B-A3B Instruct: —
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Vending-Bench 2 | 71.56 | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Qwen3 Max: 22.0 (#186), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 72.5% | 66.7% |
| LMArena Hard Prompts | 1448 | 1428 |
| NYT Connections (extended) | 30.1% | — |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 82.1% | — |
| LMCA | 28.3% | — |
| Epoch Capabilities Index | 142.41 | — |
Math Qwen3 Max leads
Qwen3 Max: 37.6 (#94), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1447 | 1440 |
| FrontierMath (Tiers 1-3) | 18.9% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| Omni-MATH | — | 46.7% |
| MATH Level 5 | 97.1% | — |
Knowledge Qwen3 Max leads
Qwen3 Max: 48.1 (#72), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1457 | 1416 |
| GPQA Diamond | 72.6% | — |
| SimpleQA Verified | 48.7% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multilingual Qwen3 Max leads
Qwen3 Max: 53.9 (#58), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1429 | 1407 |
| LMArena Chinese | 1479 | 1461 |
| LMArena French | 1450 | 1415 |
| LMArena German | 1463 | 1416 |
| LMArena Japanese | 1399 | 1398 |
| LMArena Korean | 1397 | 1366 |
| LMArena Russian | 1428 | 1403 |
| LMArena Spanish | 1463 | 1436 |
Instruction Following Qwen3 Max leads
Qwen3 Max: 75.0 (#81), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1420 | 1388 |
| IFEval | — | 81% |
Long Context Qwen3 Max leads
Qwen3 Max: 41.6 (#129), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 66.7% | 55.6% |
| LMArena Longer Query | 1439 | 1403 |
| CL-bench | 14.5% | — |
Writing & Preference Qwen3 Max leads
Qwen3 Max: 62.6 (#72), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | Qwen3 Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1439 | 1417 |
| LMArena Creative Writing | 1401 | 1333 |
| LMArena Multi-Turn | 1446 | 1415 |
| WildBench | — | 80.7% |
Frequently asked questions
Is Qwen3 Max better than Qwen3-Next 80B-A3B Instruct?
Qwen3 Max is the stronger model overall, scoring 43.5 to 42.5 on the Noometry Index. Qwen3-Next 80B-A3B Instruct costs 2.7× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3 Max or Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Qwen3 Max or Qwen3-Next 80B-A3B Instruct better for coding?
They score almost the same on coding (42.4 vs 41.9); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 131K.
How many benchmarks do Qwen3 Max and Qwen3-Next 80B-A3B Instruct share?
19 benchmarks have published results for both models. Qwen3 Max has 33 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.