Model comparison
Qwen2.5 7B Instruct vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 28.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where Qwen3.5 Max Preview leads 37.3 to 11.8.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 28.6 | 44.7 |
| Released | 2024-09 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 35.9 (#204), Qwen3.5 Max Preview: 43.4 (#79)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1488 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.5 (#117), Qwen3.5 Max Preview: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 14.3 (#317), Qwen3.5 Max Preview: 29.6 (#81)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1483 |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.44 | — |
Math Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 11.8 (#300), Qwen3.5 Max Preview: 37.3 (#99)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1473 |
Knowledge Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 17.0 (#281), Qwen3.5 Max Preview: 41.1 (#104)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1489 |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen3.5 Max Preview: 56.4 (#21)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | — | 1465 |
| LMArena Chinese | — | 1534 |
| LMArena French | — | 1483 |
| LMArena German | — | 1487 |
| LMArena Japanese | — | 1497 |
| LMArena Korean | — | 1438 |
| LMArena Russian | — | 1472 |
| LMArena Spanish | — | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 63.4 (#226), Qwen3.5 Max Preview: 77.2 (#28)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1467 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen3.5 Max Preview: 45.2 (#44)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | — | 1477 |
Writing & Preference Qwen3.5 Max Preview leads
Qwen2.5 7B Instruct: 48.8 (#194), Qwen3.5 Max Preview: 66.1 (#39)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | — | 1471 |
| LMArena Creative Writing | — | 1464 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1478 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 28.6 on the Noometry Index.
Is Qwen2.5 7B Instruct or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 43.4 versus 35.9 in the Noometry coding category.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3.5 Max Preview share?
0 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3.5 Max Preview has 17.