Model comparison
MiniMax-M2.5 vs Qwen1.5-110B
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 34.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.5 scores higher in 6 categories and Qwen1.5-110B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.5 leads 53.9 to 38.0.
Side by side
| MiniMax-M2.5 | Qwen1.5-110B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 34.2 |
| Released | 2026-02-12 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), Qwen1.5-110B: 33.0 (#264)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1381 | 1184 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Qwen1.5-110B: —
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Qwen1.5-110B leads
MiniMax-M2.5: 17.5 (#292), Qwen1.5-110B: 22.7 (#189)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1168 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |
| ForecastBench | — | 57.7 |
Math Qwen1.5-110B leads
MiniMax-M2.5: 26.9 (#253), Qwen1.5-110B: 33.7 (#201)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1378 | 1185 |
| ProofBench | 4% | — |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Qwen1.5-110B: 31.2 (#219)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1379 | 1144 |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), Qwen1.5-110B: 33.6 (#250)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1338 | 1142 |
| LMArena Chinese | 1393 | 1206 |
| LMArena French | 1362 | 1151 |
| LMArena German | 1362 | 1123 |
| LMArena Japanese | 1171 | 1074 |
| LMArena Korean | 1232 | 1044 |
| LMArena Russian | 1358 | 1118 |
| LMArena Spanish | 1354 | 1142 |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), Qwen1.5-110B: 60.3 (#252)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1158 |
Long Context MiniMax-M2.5 leads
MiniMax-M2.5: 37.5 (#216), Qwen1.5-110B: 35.1 (#242)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1366 | 1157 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), Qwen1.5-110B: 38.0 (#255)
| Benchmark | MiniMax-M2.5 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1359 | 1175 |
| LMArena Creative Writing | 1331 | 1148 |
| LMArena Multi-Turn | 1364 | 1160 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen1.5-110B?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 34.2 on the Noometry Index.
Is MiniMax-M2.5 or Qwen1.5-110B better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 33.0 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Qwen1.5-110B share?
17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen1.5-110B has 20.