Model comparison
Qwen2.5 72B Instruct vs Qwen3.5-9B
Qwen3.5-9B is the stronger model overall, scoring 33.3 to 31.5 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 1 category and Qwen3.5-9B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-9B leads 46.0 to 26.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.1% for Qwen2.5 72B Instruct and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen3.5-9B accepts more context: 262K tokens versus 131K.
Side by side
| Qwen2.5 72B Instruct | Qwen3.5-9B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.5 | 33.3 |
| Released | 2024-09 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $1.40 | $0.10 |
| Output $ / M tokens | $5.60 | $0.15 |
| Results tracked | 43 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-9B leads
Qwen2.5 72B Instruct: 32.8 (#256), Qwen3.5-9B: 35.3 (#213)
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| SciCode | — | 27.5% |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| LMArena Coding | 1293 | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 22.0 (#124), Qwen3.5-9B: 14.4 (#143)
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Qwen3.5-9B leads
Qwen2.5 72B Instruct: 21.4 (#197), Qwen3.5-9B: 22.5 (#178)
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| DTBench | 62.9% | 71.2% |
| LMCA | 13.4% | 24.5% |
| Epoch Capabilities Index | 129.01 | 139.45 |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | 1271 | — |
| BIG-Bench Hard | 79.8% | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Qwen3.5-9B leads
Qwen2.5 72B Instruct: 18.1 (#281), Qwen3.5-9B: 33.5 (#174)
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| Omni-MATH | 33% | — |
| LMArena Math | 1283 | — |
| MATH Level 5 | 63.2% | — |
Knowledge Qwen3.5-9B leads
Qwen2.5 72B Instruct: 26.9 (#247), Qwen3.5-9B: 46.0 (#77)
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 49.1% | 79% |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1245 | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Not comparable
Qwen2.5 72B Instruct: 41.2 (#208), Qwen3.5-9B: —
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1252 | — |
| LMArena Chinese | 1272 | — |
| LMArena French | 1279 | — |
| LMArena German | 1234 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1264 | — |
| LMArena Spanish | 1255 | — |
Instruction Following Not comparable
Qwen2.5 72B Instruct: 65.7 (#216), Qwen3.5-9B: —
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| IFEval | 80.6% | — |
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Qwen2.5 72B Instruct: 38.9 (#183), Qwen3.5-9B: —
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1282 | — |
Writing & Preference Not comparable
Qwen2.5 72B Instruct: 46.9 (#210), Qwen3.5-9B: —
| Benchmark | Qwen2.5 72B Instruct | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1269 | — |
| LMArena Creative Writing | 1221 | — |
| WildBench | 80.2% | — |
| LMArena Multi-Turn | 1272 | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Qwen3.5-9B?
Qwen3.5-9B is the stronger model overall, scoring 33.3 to 31.5 on the Noometry Index.
Which is cheaper, Qwen2.5 72B Instruct or Qwen3.5-9B?
Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Qwen2.5 72B Instruct or Qwen3.5-9B better for coding?
Qwen3.5-9B scores higher on coding benchmarks: 35.3 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-9B does, with 262K tokens against 131K.
How many benchmarks do Qwen2.5 72B Instruct and Qwen3.5-9B share?
5 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Qwen3.5-9B has 10.