Model comparison
Step 5 Preview vs Yi-34B
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
StepFunSummary
- They share 13 benchmarks with published results for both. Step 5 Preview 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 5 Preview leads 41.2 to 7.5.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| Step 5 Preview | Yi-34B | |
|---|---|---|
| Provider | StepFun | 01.AI |
| Noometry Index | 47.9 | 27.8 |
| Released | 2026-09-16 | 2023-11-02 |
| Weights | Proprietary | Open |
| Context window | 1.02M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $2.70 | — |
| Results tracked | 18 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Step 5 Preview: 51.8 (#36), Yi-34B: 32.3 (#274)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Coding | 1480 | 1112 |
| LMArena WebDev | 1564 | — |
| SciCode | 58.9% | — |
Reasoning Step 5 Preview leads
Step 5 Preview: 40.0 (#57), Yi-34B: 21.2 (#226)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1104 |
| CritPt | 20.9% | — |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Step 5 Preview leads
Step 5 Preview: 46.1 (#72), Yi-34B: 21.6 (#282)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Math | 1470 | 1114 |
| ProofBench | 42% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Step 5 Preview leads
Step 5 Preview: 41.2 (#112), Yi-34B: 7.5 (#309)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Expert | 1470 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |
Multimodal Not comparable
Step 5 Preview: 41.0 (#41), Yi-34B: —
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Vision | 1267 | — |
Multilingual Step 5 Preview leads
Step 5 Preview: 53.8 (#54), Yi-34B: 29.7 (#264)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Non-English | 1432 | 1079 |
| LMArena Chinese | 1519 | 1176 |
| LMArena Russian | 1436 | 1050 |
| LMArena Spanish | 1439 | 1070 |
| LMArena French | — | 1081 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
Instruction Following Step 5 Preview leads
Step 5 Preview: 76.0 (#50), Yi-34B: 56.2 (#274)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1444 | 1091 |
Long Context Step 5 Preview leads
Step 5 Preview: 44.5 (#64), Yi-34B: 33.2 (#264)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1455 | 1094 |
Writing & Preference Step 5 Preview leads
Step 5 Preview: 62.8 (#71), Yi-34B: 34.1 (#273)
| Benchmark | Step 5 Preview | Yi-34B |
|---|---|---|
| LMArena Text | 1442 | 1129 |
| LMArena Creative Writing | 1410 | 1108 |
| LMArena Multi-Turn | 1447 | 1113 |
Frequently asked questions
Is Step 5 Preview better than Yi-34B?
Step 5 Preview is the stronger model overall, scoring 47.9 to 27.8 on the Noometry Index.
Is Step 5 Preview or Yi-34B better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 32.3 in the Noometry coding category.
How many benchmarks do Step 5 Preview and Yi-34B share?
13 benchmarks have published results for both models. Step 5 Preview has 18 scored results on Noometry and Yi-34B has 23.