Model comparison
MiniMax-M2.7 vs Qwen1.5-14B
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 32.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. MiniMax-M2.7 scores higher in 6 categories and Qwen1.5-14B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 59.1 to 33.7.
Side by side
| MiniMax-M2.7 | Qwen1.5-14B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 32.1 |
| Released | 2026-03-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 30 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.4 (#115), Qwen1.5-14B: 32.5 (#259)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1454 | 1138 |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.7: 24.9 (#103), Qwen1.5-14B: —
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning Qwen1.5-14B leads
MiniMax-M2.7: 19.0 (#248), Qwen1.5-14B: 20.5 (#217)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1113 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| Epoch Capabilities Index | 145.84 | — |
Math Qwen1.5-14B leads
MiniMax-M2.7: 24.9 (#254), Qwen1.5-14B: 29.9 (#214)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1420 | 1125 |
| ProofBench | 3% | — |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.1 (#151), Qwen1.5-14B: 29.3 (#230)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1443 | 1094 |
| Vectara Hallucination Rate | 12.9% | — |
| MMLU | — | 68.6% |
Multilingual MiniMax-M2.7 leads
MiniMax-M2.7: 50.5 (#120), Qwen1.5-14B: 30.8 (#257)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1382 | 1095 |
| LMArena Chinese | 1439 | 1147 |
| LMArena French | 1422 | 1115 |
| LMArena German | 1398 | 1043 |
| LMArena Japanese | 1261 | 1019 |
| LMArena Russian | 1383 | 1046 |
| LMArena Spanish | 1403 | 1085 |
| LMArena Korean | 1313 | — |
Instruction Following MiniMax-M2.7 leads
MiniMax-M2.7: 74.2 (#101), Qwen1.5-14B: 57.1 (#266)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1102 |
Long Context MiniMax-M2.7 leads
MiniMax-M2.7: 43.3 (#94), Qwen1.5-14B: 33.7 (#252)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1419 | 1113 |
Writing & Preference MiniMax-M2.7 leads
MiniMax-M2.7: 59.1 (#107), Qwen1.5-14B: 33.7 (#270)
| Benchmark | MiniMax-M2.7 | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1404 | 1128 |
| LMArena Creative Writing | 1354 | 1091 |
| LMArena Multi-Turn | 1413 | 1110 |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen1.5-14B?
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 32.1 on the Noometry Index.
Is MiniMax-M2.7 or Qwen1.5-14B better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 32.5 in the Noometry coding category.
How many benchmarks do MiniMax-M2.7 and Qwen1.5-14B share?
16 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen1.5-14B has 17.