Model comparison
GPT-4.5 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 37.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GPT-4.5 scores higher in 6 categories and Step 3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 13.9.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 37.2 | 40.5 |
| Released | 2025-02-27 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Step 3: 40.1 (#147)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Coding | 1396 | 1367 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Step 3: —
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Step 3 leads
GPT-4.5: 13.9 (#330), Step 3: 28.4 (#105)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1355 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 62.3% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Step 3 leads
GPT-4.5: 32.6 (#211), Step 3: 37.6 (#148)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Math | 1412 | 1366 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Step 3 leads
GPT-4.5: 32.5 (#211), Step 3: 36.8 (#164)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Expert | 1394 | 1333 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal GPT-4.5 leads
GPT-4.5: 37.6 (#71), Step 3: 35.5 (#86)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Vision | 1195 | 1177 |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Step 3: 46.3 (#159)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Non-English | 1413 | 1327 |
| LMArena Chinese | 1421 | 1397 |
| LMArena German | 1457 | 1371 |
| LMArena Korean | 1392 | 1269 |
| LMArena Russian | 1419 | 1331 |
| LMArena French | 1418 | — |
| LMArena Japanese | 1416 | — |
| LMArena Spanish | — | 1371 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.6 (#134), Step 3: 70.4 (#164)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1332 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Too close to call
GPT-4.5: 40.4 (#155), Step 3: 40.3 (#157)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1326 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 56.9 (#134), Step 3: 54.3 (#151)
| Benchmark | GPT-4.5 | Step 3 |
|---|---|---|
| LMArena Text | 1417 | 1350 |
| LMArena Creative Writing | 1394 | 1321 |
| LMArena Multi-Turn | 1444 | 1341 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 37.2 on the Noometry Index.
Is GPT-4.5 or Step 3 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 40.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Step 3 share?
15 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Step 3 has 17.