Model comparison
MiniMax-M2.5 vs Qwen-14B
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. MiniMax-M2.5 scores higher in 5 categories and Qwen-14B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.5 leads 54.1 to 27.8.
Side by side
| MiniMax-M2.5 | Qwen-14B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.1 | 30.8 |
| Released | 2026-02-12 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 47.9 (#53), Qwen-14B: 30.6 (#283)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1380 | 1072 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.2 (#70), Qwen-14B: —
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Qwen-14B leads
MiniMax-M2.5: 17.6 (#281), Qwen-14B: 18.7 (#255)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1027 |
| Epoch Capabilities Index | 146.68 | 112.8 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
MiniMax-M2.5: 25.8 (#242), Qwen-14B: 28.7 (#224)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Math | 1378 | 1068 |
| ProofBench | 4% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
MiniMax-M2.5: 38.6 (#132), Qwen-14B: —
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| Vectara Hallucination Rate | 9.1% | — |
| LMArena Expert | 1378 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.3 (#147), Qwen-14B: 27.7 (#270)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1338 | 1042 |
| LMArena Chinese | 1392 | 1077 |
| LMArena French | 1363 | — |
| LMArena German | 1361 | — |
| LMArena Japanese | 1169 | — |
| LMArena Korean | 1232 | — |
| LMArena Russian | 1359 | — |
| LMArena Spanish | 1354 | — |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.7 (#143), Qwen-14B: 52.6 (#284)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1031 |
Long Context MiniMax-M2.5 leads
MiniMax-M2.5: 37.4 (#211), Qwen-14B: 31.3 (#276)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1367 | 1029 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 54.1 (#149), Qwen-14B: 27.8 (#294)
| Benchmark | MiniMax-M2.5 | Qwen-14B |
|---|---|---|
| LMArena Text | 1359 | 1051 |
| LMArena Creative Writing | 1331 | 1028 |
| LMArena Multi-Turn | 1364 | 1022 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen-14B?
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 30.8 on the Noometry Index.
Is MiniMax-M2.5 or Qwen-14B better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 30.6 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Qwen-14B share?
11 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen-14B has 18.