Model comparison
MiniMax-M2 vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 2.3× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 37.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.8% for MiniMax-M2 and 69.4% for Qwen3 235B-A22B.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- MiniMax-M2 accepts more context: 205K tokens versus 131K.
Side by side
| MiniMax-M2 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 43.5 |
| Released | 2025-10-27 | 2025-04 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.30 | $0.70 |
| Output $ / M tokens | $1.20 | $2.80 |
| Results tracked | 21 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
MiniMax-M2: 39.3 (#159), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1370 | 1445 |
| SWE-bench Verified (bash only) | 61% | — |
| Aider Polyglot | — | 59.6% |
| LMArena WebDev | 1297 | — |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Qwen3 235B-A22B leads
MiniMax-M2: 25.1 (#109), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| Vending-Bench 2 | 160.6 | -11.34 |
| Terminal-Bench | 30% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
Reasoning MiniMax-M2 leads
MiniMax-M2: 19.4 (#258), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 69.4% |
| LMArena Hard Prompts | 1357 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| NYT Connections (extended) | 14.8% | — |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
MiniMax-M2: 37.3 (#160), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1352 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
MiniMax-M2: 37.0 (#163), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Expert | 1337 | 1463 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
MiniMax-M2: 45.3 (#171), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1313 | 1409 |
| LMArena Chinese | 1366 | 1481 |
| LMArena French | 1335 | 1445 |
| LMArena German | 1355 | 1433 |
| LMArena Russian | 1331 | 1411 |
| LMArena Spanish | 1326 | 1430 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1391 |
Instruction Following Qwen3 235B-A22B leads
MiniMax-M2: 70.2 (#166), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1328 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
MiniMax-M2: 40.5 (#153), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1331 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
MiniMax-M2: 53.0 (#162), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | MiniMax-M2 | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1340 | 1419 |
| LMArena Creative Writing | 1286 | 1384 |
| LMArena Multi-Turn | 1361 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
Frequently asked questions
Is MiniMax-M2 better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 2.3× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2 or Qwen3 235B-A22B?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is MiniMax-M2 or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 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 235B-A22B share?
17 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3 235B-A22B has 49.