Model comparison
MiniMax-M2.7 vs Qwen3 8B
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.7 on the Noometry Index. Qwen3 8B 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 . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. MiniMax-M2.7 scores higher in 4 categories and Qwen3 8B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 8B leads 34.9 to 25.9.
- The biggest single-benchmark swing is SciCode: 47% for MiniMax-M2.7 and 22.6% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $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 | Qwen3 8B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 33.7 |
| Released | 2026-03-18 | 2025-04 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $0.18 |
| Output $ / M tokens | $1.20 | $0.70 |
| Results tracked | 30 | 11 |
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), Qwen3 8B: 34.0 (#248)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| SciCode | 47% | 22.6% |
| LMArena WebDev | 1398 | — |
| WeirdML | 37% | — |
| LMArena Coding | 1454 | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Qwen3 8B leads
MiniMax-M2.7: 25.1 (#111), Qwen3 8B: 30.2 (#78)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| Berkeley Function Calling Leaderboard | — | 42.6% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning MiniMax-M2.7 leads
MiniMax-M2.7: 19.7 (#253), Qwen3 8B: 16.6 (#303)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| CritPt | 0.6% | 0% |
| Epoch Capabilities Index | 145.85 | 136.17 |
| NYT Connections (extended) | 24.7% | — |
| Chess Puzzles | — | 5% |
| Thematic Generalization | 39.3% | — |
| LMArena Hard Prompts | 1422 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
Math Qwen3 8B leads
MiniMax-M2.7: 25.9 (#263), Qwen3 8B: 34.9 (#191)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| ProofBench | 3% | — |
| LMArena Math | 1420 | — |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.7 (#152), Qwen3 8B: 36.1 (#173)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 4.8% |
| GPQA Diamond | — | 56.8% |
| LMArena Expert | 1444 | — |
Multilingual Not comparable
MiniMax-M2.7: 50.3 (#123), Qwen3 8B: —
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| 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 Not comparable
MiniMax-M2.7: 74.1 (#103), Qwen3 8B: —
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1405 | — |
Long Context MiniMax-M2.7 leads
MiniMax-M2.7: 43.3 (#99), Qwen3 8B: 37.9 (#210)
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1419 | — |
Writing & Preference Not comparable
MiniMax-M2.7: 58.9 (#112), Qwen3 8B: —
| Benchmark | MiniMax-M2.7 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1405 | — |
| LMArena Creative Writing | 1354 | — |
| LMArena Multi-Turn | 1412 | — |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen3 8B?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.7 on the Noometry Index. Qwen3 8B 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 Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 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 Qwen3 8B better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 34.0 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 Qwen3 8B share?
4 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3 8B has 11.