Model comparison
MiniMax-M2.5 vs Qwen3 8B
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 33.7 on the Noometry Index. Qwen3 8B costs 1.7× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. MiniMax-M2.5 scores higher in 4 categories and Qwen3 8B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 34.0.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- MiniMax-M2.5 accepts more context: 205K tokens versus 131K.
Side by side
| MiniMax-M2.5 | Qwen3 8B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 33.7 |
| Released | 2026-02-12 | 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 | 33 | 11 |
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), Qwen3 8B: 34.0 (#248)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| SciCode | — | 22.6% |
| LMArena Coding | 1381 | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Too close to call
MiniMax-M2.5: 30.4 (#77), Qwen3 8B: 30.2 (#78)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Berkeley Function Calling Leaderboard | — | 42.6% |
| Vending-Bench 2 | -23.16 | — |
Reasoning Too close to call
MiniMax-M2.5: 17.5 (#292), Qwen3 8B: 16.6 (#303)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| Epoch Capabilities Index | 146.68 | 136.17 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1372 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
Math Qwen3 8B leads
MiniMax-M2.5: 26.9 (#253), Qwen3 8B: 34.9 (#191)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| ProofBench | 4% | — |
| LMArena Math | 1378 | — |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Qwen3 8B: 36.1 (#173)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| Vectara Hallucination Rate | 9.1% | 4.8% |
| GPQA Diamond | — | 56.8% |
| LMArena Expert | 1379 | — |
Multilingual Not comparable
MiniMax-M2.5: 47.1 (#152), Qwen3 8B: —
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1338 | — |
| LMArena Chinese | 1393 | — |
| LMArena French | 1362 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1171 | — |
| LMArena Korean | 1232 | — |
| LMArena Russian | 1358 | — |
| LMArena Spanish | 1354 | — |
Instruction Following Not comparable
MiniMax-M2.5: 71.5 (#148), Qwen3 8B: —
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1353 | — |
Long Context Too close to call
MiniMax-M2.5: 37.5 (#216), Qwen3 8B: 37.9 (#210)
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
| LMArena Longer Query | 1366 | — |
Writing & Preference Not comparable
MiniMax-M2.5: 53.9 (#153), Qwen3 8B: —
| Benchmark | MiniMax-M2.5 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1359 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1364 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen3 8B?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 33.7 on the Noometry Index. Qwen3 8B costs 1.7× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.5 or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is MiniMax-M2.5 or Qwen3 8B better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 131K.
How many benchmarks do MiniMax-M2.5 and Qwen3 8B share?
2 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3 8B has 11.