Model comparison
MiniMax-M2.5 vs Qwen3.5 Plus
Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 1.7× less per token, which makes it the better buy when Qwen3.5 Plus's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. MiniMax-M2.5 scores higher in 0 categories and Qwen3.5 Plus in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 Plus leads 47.9 to 25.8.
- The biggest single-benchmark swing is CL-bench: 11.4% for MiniMax-M2.5 and 19.8% for Qwen3.5 Plus.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $2.40 for Qwen3.5 Plus.
- Qwen3.5 Plus accepts more context: 1M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Qwen3.5 Plus | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.1 | 42.3 |
| Released | 2026-02-12 | 2026-02-16 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $1.20 | $2.40 |
| Results tracked | 33 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M2.5: 47.9 (#53), Qwen3.5 Plus: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| ALE-Bench | 618.17 | 621.92 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| LMArena Coding | 1380 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.2 (#70), Qwen3.5 Plus: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| Vending-Bench 2 | -23.16 | 0.54 |
| Terminal-Bench | 42.7% | — |
Reasoning Qwen3.5 Plus leads
MiniMax-M2.5: 17.6 (#281), Qwen3.5 Plus: 32.0 (#67)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| Epoch Capabilities Index | 146.68 | 146.79 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | — | 22% |
| LMArena Hard Prompts | 1372 | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 80.5% |
| LMCA | — | 36.4% |
Math Qwen3.5 Plus leads
MiniMax-M2.5: 25.8 (#242), Qwen3.5 Plus: 47.9 (#55)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | 4% | — |
| LMArena Math | 1378 | — |
| FrontierMath (Feb 2025 set) | — | 21% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Qwen3.5 Plus leads
MiniMax-M2.5: 38.6 (#132), Qwen3.5 Plus: 46.0 (#78)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| Vectara Hallucination Rate | 9.1% | 10.7% |
| GPQA Diamond | — | 84.8% |
| SimpleQA Verified | — | 25.4% |
| LMArena Expert | 1378 | — |
Multilingual Not comparable
MiniMax-M2.5: 47.3 (#147), Qwen3.5 Plus: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Non-English | 1338 | — |
| LMArena Chinese | 1392 | — |
| LMArena French | 1363 | — |
| LMArena German | 1361 | — |
| LMArena Japanese | 1169 | — |
| LMArena Korean | 1232 | — |
| LMArena Russian | 1359 | — |
| LMArena Spanish | 1354 | — |
Instruction Following Not comparable
MiniMax-M2.5: 71.7 (#143), Qwen3.5 Plus: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Instruction Following | 1353 | — |
Long Context Qwen3.5 Plus leads
MiniMax-M2.5: 37.4 (#211), Qwen3.5 Plus: 42.9 (#109)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| CL-bench | 11.4% | 19.8% |
| CL-bench Life | 6.3% | 12.4% |
| LMArena Longer Query | 1367 | — |
Writing & Preference Not comparable
MiniMax-M2.5: 54.1 (#149), Qwen3.5 Plus: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Text | 1359 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1364 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen3.5 Plus?
Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 1.7× less per token, which makes it the better buy when Qwen3.5 Plus's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.5 or Qwen3.5 Plus?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 Plus lists at $0.40 and $2.40.
Which has the bigger context window?
Qwen3.5 Plus does, with 1M tokens against 205K.
How many benchmarks do MiniMax-M2.5 and Qwen3.5 Plus share?
6 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3.5 Plus has 15.