Model comparison
MiniMax-M2.7 vs Qwen2.5 7B Instruct
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 1.7× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. MiniMax-M2.7 scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 17.0.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- MiniMax-M2.7 accepts more context: 205K tokens versus 131K.
Side by side
| MiniMax-M2.7 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 29.0 |
| Released | 2026-03-18 | 2024-09 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $0.17 |
| Output $ / M tokens | $1.20 | $0.70 |
| Results tracked | 30 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.8 (#120), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1454 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use MiniMax-M2.7 leads
MiniMax-M2.7: 25.1 (#111), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| BALROG | — | 7.8% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning MiniMax-M2.7 leads
MiniMax-M2.7: 19.7 (#253), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 145.85 | 118.51 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 0% |
| Thematic Generalization | 39.3% | — |
| LMArena Hard Prompts | 1422 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
Math MiniMax-M2.7 leads
MiniMax-M2.7: 25.9 (#263), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| ProofBench | 3% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1420 | — |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.7 (#152), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1444 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
MiniMax-M2.7: 50.3 (#123), Qwen2.5 7B Instruct: —
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1382 | — |
| LMArena Chinese | 1441 | — |
| LMArena French | 1421 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1313 | — |
| LMArena Russian | 1383 | — |
| LMArena Spanish | 1403 | — |
Instruction Following MiniMax-M2.7 leads
MiniMax-M2.7: 74.1 (#103), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
MiniMax-M2.7: 43.3 (#99), Qwen2.5 7B Instruct: —
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1419 | — |
Writing & Preference MiniMax-M2.7 leads
MiniMax-M2.7: 58.9 (#112), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | MiniMax-M2.7 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1405 | — |
| LMArena Creative Writing | 1354 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1412 | — |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen2.5 7B Instruct?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 1.7× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.7 or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is MiniMax-M2.7 or Qwen2.5 7B Instruct better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.7 does, with 205K tokens against 131K.
How many benchmarks do MiniMax-M2.7 and Qwen2.5 7B Instruct share?
1 benchmark has published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen2.5 7B Instruct has 15.