Model comparison
Qwen2.5 32B Instruct vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in math, where Step 3 leads 34.9 to 15.3.
Side by side
| Qwen2.5 32B Instruct | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 29.7 | 39.9 |
| Released | 2024-09 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen2.5 32B Instruct: 38.1 (#165), Step 3: 39.5 (#144)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| BigCodeBench Instruct | 45% | — |
| LMArena Coding | — | 1367 |
| BigCodeBench Complete | 52.3% | — |
Reasoning Step 3 leads
Qwen2.5 32B Instruct: 18.5 (#262), Step 3: 27.6 (#102)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1355 |
| Epoch Capabilities Index | 128.52 | — |
Math Step 3 leads
Qwen2.5 32B Instruct: 15.3 (#289), Step 3: 34.9 (#148)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.4% | — |
| LMArena Math | — | 1366 |
| MATH Level 5 | 56.1% | — |
Knowledge Step 3 leads
Qwen2.5 32B Instruct: 24.9 (#259), Step 3: 36.2 (#161)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| GPQA Diamond | 46.1% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Qwen2.5 32B Instruct: —, Step 3: 34.9 (#81)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Qwen2.5 32B Instruct: —, Step 3: 46.5 (#154)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
Qwen2.5 32B Instruct: —, Step 3: 70.6 (#159)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Qwen2.5 32B Instruct: —, Step 3: 40.3 (#152)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Qwen2.5 32B Instruct: —, Step 3: 54.5 (#146)
| Benchmark | Qwen2.5 32B Instruct | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Qwen2.5 32B Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 29.7 on the Noometry Index.
Is Qwen2.5 32B Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Qwen2.5 32B Instruct and Step 3 share?
0 benchmarks have published results for both models. Qwen2.5 32B Instruct has 7 scored results on Noometry and Step 3 has 17.