Model comparison
Qwen2.5 7B Instruct vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 29.0 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 4 categories and Qwen2-72B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 12.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 46.1% for Qwen2.5 7B Instruct and 54% for Qwen2-72B.
Side by side
| Qwen2.5 7B Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 30.0 |
| Released | 2024-09 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 36.5 (#208), Qwen2-72B: 29.1 (#310)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 38.5% |
| BigCodeBench Complete | 46.1% | 54% |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
Agentic & Tool Use Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 23.8 (#124), Qwen2-72B: 17.0 (#146)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| BALROG | 7.8% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Qwen2.5 7B Instruct: 14.8 (#322), Qwen2-72B: 23.2 (#181)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 118.51 | 125.28 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1191 |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
Math Qwen2-72B leads
Qwen2.5 7B Instruct: 12.6 (#306), Qwen2-72B: 30.2 (#236)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Qwen2-72B leads
Qwen2.5 7B Instruct: 17.0 (#286), Qwen2-72B: 21.2 (#275)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 35.5% | 40.8% |
| MMLU | 72.9% | 82.4% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1171 |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 63.2 (#231), Qwen2-72B: 61.7 (#241)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Qwen2.5 7B Instruct leads
Qwen2.5 7B Instruct: 48.8 (#195), Qwen2-72B: 40.8 (#241)
| Benchmark | Qwen2.5 7B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 29.0 on the Noometry Index.
Is Qwen2.5 7B Instruct or Qwen2-72B better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2.5 7B Instruct and Qwen2-72B share?
5 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen2-72B has 26.