Model comparison
o1 vs Step 3
o1 and Step 3 score almost the same on the Noometry Index (40.6 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. o1 scores higher in 6 categories and Step 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where o1 leads 50.3 to 40.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| o1 | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 40.6 | 39.9 |
| Released | 2024-09-12 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 52 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
o1: 45.7 (#64), Step 3: 39.5 (#144)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Coding | 1367 | 1367 |
| Aider Polyglot | 61.7% | — |
| WeirdML | 47.6% | — |
| LiveBench Coding | 69.7% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |
Agentic & Tool Use Not comparable
o1: 24.3 (#111), Step 3: —
| Benchmark | o1 | Step 3 |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |
Reasoning Too close to call
o1: 27.5 (#103), Step 3: 27.6 (#102)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1355 |
| SimpleBench | 41.7% | — |
| Kagi LLM Benchmark | — | 62.3% |
| ARC-AGI-1 | 30.7% | — |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| LiveBench Reasoning | 91.6% | — |
| DTBench | 74.7% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | 22.3% | — |
| Epoch Capabilities Index | 141.92 | — |
| LiveBench | 75.7% | — |
Math Too close to call
o1: 34.9 (#150), Step 3: 34.9 (#148)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Math | 1388 | 1366 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LiveBench Math | 80.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |
Knowledge o1 leads
o1: 41.5 (#101), Step 3: 36.2 (#161)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Expert | 1362 | 1333 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |
Multimodal Step 3 leads
o1: 33.6 (#87), Step 3: 34.9 (#81)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Vision | 1168 | 1176 |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |
Multilingual o1 leads
o1: 48.8 (#137), Step 3: 46.5 (#154)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1359 | 1327 |
| LMArena Chinese | 1394 | 1396 |
| LMArena German | 1337 | 1371 |
| LMArena Korean | 1396 | 1271 |
| LMArena Russian | 1356 | 1331 |
| LMArena Spanish | 1345 | 1372 |
| LMArena French | 1343 | — |
| LMArena Japanese | 1346 | — |
Instruction Following o1 leads
o1: 75.0 (#82), Step 3: 70.6 (#159)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1368 | 1332 |
| LiveBench Instruction Following | 81.5% | — |
Long Context o1 leads
o1: 50.3 (#9), Step 3: 40.3 (#152)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1378 | 1326 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference o1 leads
o1: 55.8 (#139), Step 3: 54.5 (#146)
| Benchmark | o1 | Step 3 |
|---|---|---|
| LMArena Text | 1366 | 1351 |
| LMArena Creative Writing | 1347 | 1322 |
| LMArena Multi-Turn | 1368 | 1340 |
| Short-Story Creative Writing | 70.2% | — |
| LiveBench Language | 65.4% | — |
Frequently asked questions
Is o1 better than Step 3?
o1 and Step 3 score almost the same on the Noometry Index (40.6 vs 39.9), so choose on price, context window or the category you care about most.
Is o1 or Step 3 better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 39.5 in the Noometry coding category.
How many benchmarks do o1 and Step 3 share?
16 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Step 3 has 17.