Model comparison
MiniMax-M2 vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 37.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 2 categories and Qwen3-30B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiniMax-M2 leads 40.5 to 31.0.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 41K.
Side by side
| MiniMax-M2 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 38.9 |
| Released | 2025-10-27 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 205K | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.30 | $0.12 |
| Output $ / M tokens | $1.20 | $0.50 |
| Results tracked | 21 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1370 | 1416 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Qwen3-30B-A3B leads
MiniMax-M2: 25.1 (#109), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Vending-Bench 2 | 160.6 | — |
Reasoning Qwen3-30B-A3B leads
MiniMax-M2: 19.4 (#258), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 54.9% |
| LMArena Hard Prompts | 1357 | 1398 |
| NYT Connections (extended) | 14.8% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Too close to call
MiniMax-M2: 37.3 (#160), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1352 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Qwen3-30B-A3B leads
MiniMax-M2: 37.0 (#163), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1337 | 1396 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multilingual Qwen3-30B-A3B leads
MiniMax-M2: 45.3 (#171), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1313 | 1372 |
| LMArena Chinese | 1366 | 1433 |
| LMArena French | 1335 | 1418 |
| LMArena German | 1355 | 1380 |
| LMArena Russian | 1331 | 1370 |
| LMArena Spanish | 1326 | 1404 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
Instruction Following Qwen3-30B-A3B leads
MiniMax-M2: 70.2 (#166), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1328 | 1363 |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#153), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1331 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
MiniMax-M2: 53.0 (#162), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | MiniMax-M2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1340 | 1384 |
| LMArena Creative Writing | 1286 | 1317 |
| LMArena Multi-Turn | 1361 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is MiniMax-M2 better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 37.4 on the Noometry Index.
Which is cheaper, MiniMax-M2 or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is MiniMax-M2 or Qwen3-30B-A3B better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 41K.
How many benchmarks do MiniMax-M2 and Qwen3-30B-A3B share?
16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3-30B-A3B has 32.