Model comparison
Qwen Max vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 34.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen Max scores higher in 1 category and Qwen3-Next 80B-A3B Instruct in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Next 80B-A3B Instruct leads 36.3 to 21.0.
- The biggest single-benchmark swing is Fiction.LiveBench: 66.7% for Qwen 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 $1.60 / $6.40 for Qwen Max.
- Qwen3-Next 80B-A3B Instruct accepts more context: 131K tokens versus 33K.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen Max | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.4 | 42.5 |
| Released | 2024-04-03 | 2025-09 |
| Weights | Proprietary | Open |
| Context window | 33K | 131K |
| Max output | 8K | 33K |
| Input $ / M tokens | $1.60 | $0.50 |
| Output $ / M tokens | $6.40 | $2 |
| Results tracked | 23 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 30.3 (#288), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1288 | 1441 |
| Aider Polyglot | 21.8% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 24.1 (#154), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
Math Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 21.0 (#272), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1275 | 1440 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| Omni-MATH | — | 46.7% |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 30.3 (#222), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1248 | 1416 |
| GPQA Diamond | 56.1% | — |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multilingual Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 42.0 (#197), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1263 | 1407 |
| LMArena Chinese | 1254 | 1461 |
| LMArena French | 1329 | 1415 |
| LMArena German | 1254 | 1416 |
| LMArena Japanese | 1205 | 1398 |
| LMArena Korean | 1141 | 1366 |
| LMArena Russian | 1274 | 1403 |
| LMArena Spanish | 1290 | 1436 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 66.7 (#203), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1262 | 1388 |
| IFEval | — | 81% |
Long Context Qwen Max leads
Qwen Max: 39.4 (#175), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 66.7% | 55.6% |
| LMArena Longer Query | 1289 | 1403 |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
Qwen Max: 48.0 (#200), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | Qwen Max | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1282 | 1417 |
| LMArena Creative Writing | 1248 | 1333 |
| LMArena Multi-Turn | 1277 | 1415 |
| WildBench | — | 80.7% |
Frequently asked questions
Is Qwen Max better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 34.4 on the Noometry Index.
Which is cheaper, Qwen 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; Qwen Max lists at $1.60 and $6.40.
Is Qwen Max or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 41.9 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Next 80B-A3B Instruct does, with 131K tokens against 33K.
How many benchmarks do Qwen Max and Qwen3-Next 80B-A3B Instruct share?
18 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.