Model comparison
Qwen1.5-110B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 34.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. Qwen1.5-110B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 38.0.
Side by side
| Qwen1.5-110B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 34.2 | 40.5 |
| Released | 2024-04-25 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 20 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen1.5-110B: 33.0 (#264), Step 3: 40.1 (#147)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Coding | 1184 | 1367 |
| BigCodeBench Instruct | 35% | — |
| BigCodeBench Complete | 44.4% | — |
Reasoning Step 3 leads
Qwen1.5-110B: 22.7 (#189), Step 3: 28.4 (#105)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1168 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| ForecastBench | 57.7 | — |
Math Step 3 leads
Qwen1.5-110B: 33.7 (#201), Step 3: 37.6 (#148)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Math | 1185 | 1366 |
Knowledge Step 3 leads
Qwen1.5-110B: 31.2 (#219), Step 3: 36.8 (#164)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Expert | 1144 | 1333 |
Multimodal Not comparable
Qwen1.5-110B: —, Step 3: 35.5 (#86)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Qwen1.5-110B: 33.6 (#250), Step 3: 46.3 (#159)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Non-English | 1142 | 1327 |
| LMArena Chinese | 1206 | 1397 |
| LMArena German | 1123 | 1371 |
| LMArena Korean | 1044 | 1269 |
| LMArena Russian | 1118 | 1331 |
| LMArena Spanish | 1142 | 1371 |
| LMArena French | 1151 | — |
| LMArena Japanese | 1074 | — |
Instruction Following Step 3 leads
Qwen1.5-110B: 60.3 (#252), Step 3: 70.4 (#164)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1158 | 1332 |
Long Context Step 3 leads
Qwen1.5-110B: 35.1 (#242), Step 3: 40.3 (#157)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1157 | 1326 |
Writing & Preference Step 3 leads
Qwen1.5-110B: 38.0 (#255), Step 3: 54.3 (#151)
| Benchmark | Qwen1.5-110B | Step 3 |
|---|---|---|
| LMArena Text | 1175 | 1350 |
| LMArena Creative Writing | 1148 | 1321 |
| LMArena Multi-Turn | 1160 | 1341 |
Frequently asked questions
Is Qwen1.5-110B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 34.2 on the Noometry Index.
Is Qwen1.5-110B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.0 in the Noometry coding category.
How many benchmarks do Qwen1.5-110B and Step 3 share?
15 benchmarks have published results for both models. Qwen1.5-110B has 20 scored results on Noometry and Step 3 has 17.