Model comparison
MiniMax-M2.5 vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. MiniMax-M2.5 scores higher in 1 category and Qwen3.5-Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 32.9 to 17.6.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- Qwen3.5-Flash accepts more context: 1M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Qwen3.5-Flash | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.1 | 42.3 |
| Released | 2026-02-12 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $1.20 | $0.40 |
| Results tracked | 33 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 47.9 (#53), Qwen3.5-Flash: 33.9 (#234)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1386 | 1243 |
| LMArena Coding | 1380 | 1412 |
| ALE-Bench | 618.17 | 221.8 |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 68.3% | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.2 (#70), Qwen3.5-Flash: —
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | -23.16 | 462.69 |
| Terminal-Bench | 42.7% | — |
Reasoning Qwen3.5-Flash leads
MiniMax-M2.5: 17.6 (#281), Qwen3.5-Flash: 32.9 (#63)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1404 |
| Epoch Capabilities Index | 146.68 | 143.98 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | — | 21% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
Math Qwen3.5-Flash leads
MiniMax-M2.5: 25.8 (#242), Qwen3.5-Flash: 36.3 (#117)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Math | 1378 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| ProofBench | 4% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
MiniMax-M2.5: 38.6 (#132), Qwen3.5-Flash: 43.2 (#84)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| Vectara Hallucination Rate | 9.1% | 10.5% |
| LMArena Expert | 1378 | 1408 |
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 20.3% |
Multilingual Qwen3.5-Flash leads
MiniMax-M2.5: 47.3 (#147), Qwen3.5-Flash: 50.7 (#116)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1338 | 1385 |
| LMArena Chinese | 1392 | 1446 |
| LMArena French | 1363 | 1412 |
| LMArena German | 1361 | 1389 |
| LMArena Japanese | 1169 | 1369 |
| LMArena Korean | 1232 | 1344 |
| LMArena Russian | 1359 | 1379 |
| LMArena Spanish | 1354 | 1399 |
Instruction Following Qwen3.5-Flash leads
MiniMax-M2.5: 71.7 (#143), Qwen3.5-Flash: 72.8 (#133)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1353 | 1374 |
Long Context Qwen3.5-Flash leads
MiniMax-M2.5: 37.4 (#211), Qwen3.5-Flash: 42.4 (#119)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1367 | 1392 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference Qwen3.5-Flash leads
MiniMax-M2.5: 54.1 (#149), Qwen3.5-Flash: 58.2 (#117)
| Benchmark | MiniMax-M2.5 | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1359 | 1397 |
| LMArena Creative Writing | 1331 | 1343 |
| LMArena Multi-Turn | 1364 | 1393 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Which is cheaper, MiniMax-M2.5 or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is MiniMax-M2.5 or Qwen3.5-Flash better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 33.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 205K.
How many benchmarks do MiniMax-M2.5 and Qwen3.5-Flash share?
22 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3.5-Flash has 32.