Model comparison
MiniMax-M2 vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.7× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and Qwen3-Next 80B-A3B Instruct in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 31.1 to 19.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.8% for MiniMax-M2 and 66.7% for Qwen3-Next 80B-A3B Instruct.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
- MiniMax-M2 accepts more context: 205K tokens versus 131K.
Side by side
| MiniMax-M2 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 43.0 |
| Released | 2025-10-27 | 2025-09 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 33K |
| Input $ / M tokens | $0.30 | $0.50 |
| Output $ / M tokens | $1.20 | $2 |
| Results tracked | 21 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 39.3 (#159), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1370 | 1440 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 19.4 (#258), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 66.7% |
| LMArena Hard Prompts | 1357 | 1428 |
| NYT Connections (extended) | 14.8% | — |
Math Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 37.3 (#160), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1352 | 1440 |
| Omni-MATH | — | 46.7% |
Knowledge Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 37.0 (#163), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1337 | 1417 |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multilingual Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 45.3 (#171), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1407 |
| LMArena Chinese | 1366 | 1460 |
| LMArena French | 1335 | 1413 |
| LMArena German | 1355 | 1417 |
| LMArena Russian | 1331 | 1404 |
| LMArena Spanish | 1326 | 1435 |
| LMArena Japanese | — | 1395 |
| LMArena Korean | — | 1364 |
Instruction Following Too close to call
MiniMax-M2: 70.2 (#166), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1328 | 1389 |
| IFEval | — | 81% |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#153), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1331 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
MiniMax-M2: 53.0 (#162), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | MiniMax-M2 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1340 | 1417 |
| LMArena Creative Writing | 1286 | 1334 |
| LMArena Multi-Turn | 1361 | 1416 |
| WildBench | — | 80.7% |
Frequently asked questions
Is MiniMax-M2 better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.7× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2 or Qwen3-Next 80B-A3B Instruct?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is MiniMax-M2 or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 131K.
How many benchmarks do MiniMax-M2 and Qwen3-Next 80B-A3B Instruct share?
16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.