Model comparison
Qwen2.5 7B Instruct vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 28.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Qwen2.5 7B Instruct scores higher in 0 categories and Qwen2.5-Max in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 34.3 to 11.8.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 28.6 | 40.1 |
| Released | 2024-09 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.17 | — |
| Output $ / M tokens | $0.70 | — |
| Results tracked | 15 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Qwen2.5 7B Instruct: 35.9 (#204), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LiveBench Coding | — | 64.4% |
| LMArena Coding | — | 1359 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.5 (#117), Qwen2.5-Max: —
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Qwen2.5-Max leads
Qwen2.5 7B Instruct: 14.3 (#317), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| Epoch Capabilities Index | 118.44 | 132.54 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| LMArena Hard Prompts | — | 1360 |
| DTBench | 47.7% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 6.4% | — |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Qwen2.5 7B Instruct: 11.8 (#300), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | 29.4% | — |
| LiveBench Math | — | 58.4% |
| LMArena Math | — | 1369 |
Knowledge Qwen2.5-Max leads
Qwen2.5 7B Instruct: 17.0 (#281), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| Confabulations | — | 21.8% |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1337 |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen2.5-Max: 48.3 (#140)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | — | 1352 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |
| LMArena Russian | — | 1353 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
Qwen2.5 7B Instruct: 63.4 (#226), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1335 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen2.5-Max: 41.3 (#137)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | — | 1358 |
Writing & Preference Qwen2.5-Max leads
Qwen2.5 7B Instruct: 48.8 (#194), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Qwen2.5 7B Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Text | — | 1367 |
| LMArena Creative Writing | — | 1339 |
| Short-Story Creative Writing | — | 72.9% |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1364 |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 28.6 on the Noometry Index.
Is Qwen2.5 7B Instruct or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 35.9 in the Noometry coding category.
How many benchmarks do Qwen2.5 7B Instruct and Qwen2.5-Max share?
1 benchmark has published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen2.5-Max has 27.