Model comparison
Step 3 vs Yi-34B
Step 3 is the stronger model overall, scoring 40.5 to 27.8 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-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.8 to 7.5.
Side by side
| Step 3 | Yi-34B | |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 40.5 | 27.8 |
| Released | — | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 23 |
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-34B: 32.3 (#274)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Coding | 1367 | 1112 |
Reasoning Step 3 leads
Step 3: 28.4 (#105), Yi-34B: 21.2 (#226)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1355 | 1104 |
| Kagi LLM Benchmark | 62.3% | — |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Step 3 leads
Step 3: 37.6 (#148), Yi-34B: 21.6 (#282)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Math | 1366 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Step 3 leads
Step 3: 36.8 (#164), Yi-34B: 7.5 (#309)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Expert | 1333 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |
Multimodal Not comparable
Step 3: 35.5 (#86), Yi-34B: —
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Vision | 1177 | — |
Multilingual Step 3 leads
Step 3: 46.3 (#159), Yi-34B: 29.7 (#264)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Non-English | 1327 | 1079 |
| LMArena Chinese | 1397 | 1176 |
| LMArena German | 1371 | 1042 |
| LMArena Korean | 1269 | 959 |
| LMArena Russian | 1331 | 1050 |
| LMArena Spanish | 1371 | 1070 |
| LMArena French | — | 1081 |
| LMArena Japanese | — | 993 |
Instruction Following Step 3 leads
Step 3: 70.4 (#164), Yi-34B: 56.2 (#274)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1332 | 1091 |
Long Context Step 3 leads
Step 3: 40.3 (#157), Yi-34B: 33.2 (#264)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1326 | 1094 |
Writing & Preference Step 3 leads
Step 3: 54.3 (#151), Yi-34B: 34.1 (#273)
| Benchmark | Step 3 | Yi-34B |
|---|---|---|
| LMArena Text | 1350 | 1129 |
| LMArena Creative Writing | 1321 | 1108 |
| LMArena Multi-Turn | 1341 | 1113 |
Frequently asked questions
Is Step 3 better than Yi-34B?
Step 3 is the stronger model overall, scoring 40.5 to 27.8 on the Noometry Index.
Is Step 3 or Yi-34B better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 32.3 in the Noometry coding category.
How many benchmarks do Step 3 and Yi-34B share?
15 benchmarks have published results for both models. Step 3 has 17 scored results on Noometry and Yi-34B has 23.