Model comparison
Step 3 vs Yi-1.5-34B
Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Step 3 scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 14.8.
Side by side
| Step 3 | Yi-1.5-34B | |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 40.5 | 30.6 |
| Released | — | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Step 3: 40.1 (#147), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1367 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Step 3 leads
Step 3: 28.4 (#105), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1160 |
| Kagi LLM Benchmark | 62.3% | — |
Math Step 3 leads
Step 3: 37.6 (#148), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1366 | 1182 |
| MATH Level 5 | — | 25.5% |
Knowledge Step 3 leads
Step 3: 36.8 (#164), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1333 | 1144 |
| GPQA Diamond | — | 32% |
Multimodal Not comparable
Step 3: 35.5 (#86), Yi-1.5-34B: —
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Vision | 1177 | — |
Multilingual Step 3 leads
Step 3: 46.3 (#159), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1327 | 1121 |
| LMArena Chinese | 1397 | 1213 |
| LMArena German | 1371 | 1111 |
| LMArena Korean | 1269 | 1005 |
| LMArena Russian | 1331 | 1091 |
| LMArena Spanish | 1371 | 1121 |
| LMArena French | — | 1156 |
| LMArena Japanese | — | 1021 |
Instruction Following Step 3 leads
Step 3: 70.4 (#164), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1332 | 1139 |
Long Context Step 3 leads
Step 3: 40.3 (#157), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1326 | 1143 |
Writing & Preference Step 3 leads
Step 3: 54.3 (#151), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Step 3 | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1350 | 1173 |
| LMArena Creative Writing | 1321 | 1135 |
| LMArena Multi-Turn | 1341 | 1153 |
Frequently asked questions
Is Step 3 better than Yi-1.5-34B?
Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.
Is Step 3 or Yi-1.5-34B better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 32.4 in the Noometry coding category.
How many benchmarks do Step 3 and Yi-1.5-34B share?
15 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Yi-1.5-34B has 21.