Model comparison
Phi 3 Small 8k Instruct vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 29.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Microsoft
StepFunSummary
- They share 15 benchmarks with published results for both. Phi 3 Small 8k Instruct 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 31.1.
Side by side
| Phi 3 Small 8k Instruct | Step 3 | |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 29.3 | 40.5 |
| Released | 2024-04-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Phi 3 Small 8k Instruct: 27.9 (#318), Step 3: 40.1 (#147)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1101 | 1367 |
| LiveBench Coding | 20.3% | — |
Reasoning Step 3 leads
Phi 3 Small 8k Instruct: 14.8 (#323), Step 3: 28.4 (#105)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 15.9% | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Step 3 leads
Phi 3 Small 8k Instruct: 27.6 (#248), Step 3: 37.6 (#148)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1151 | 1366 |
| LiveBench Math | 17.6% | — |
Knowledge Step 3 leads
Phi 3 Small 8k Instruct: 29.1 (#240), Step 3: 36.8 (#164)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1067 | 1333 |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multimodal Not comparable
Phi 3 Small 8k Instruct: —, Step 3: 35.5 (#86)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Phi 3 Small 8k Instruct: 28.5 (#272), Step 3: 46.3 (#159)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1058 | 1327 |
| LMArena Chinese | 1061 | 1397 |
| LMArena German | 1080 | 1371 |
| LMArena Korean | 894 | 1269 |
| LMArena Russian | 1111 | 1331 |
| LMArena Spanish | 1111 | 1371 |
| LMArena French | 1135 | — |
| LMArena Japanese | 966 | — |
Instruction Following Step 3 leads
Phi 3 Small 8k Instruct: 51.9 (#292), Step 3: 70.4 (#164)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1087 | 1332 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Step 3 leads
Phi 3 Small 8k Instruct: 33.0 (#267), Step 3: 40.3 (#157)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1088 | 1326 |
Writing & Preference Step 3 leads
Phi 3 Small 8k Instruct: 31.1 (#284), Step 3: 54.3 (#151)
| Benchmark | Phi 3 Small 8k Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1110 | 1350 |
| LMArena Creative Writing | 1083 | 1321 |
| LMArena Multi-Turn | 1068 | 1341 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Step 3 share?
15 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Step 3 has 17.