Model comparison
o3 vs Step 1o Turbo 202506
o3 is the stronger model overall, scoring 47.5 to 39.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. o3 scores higher in 9 categories and Step 1o Turbo 202506 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 36.1.
Side by side
| o3 | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 47.5 | 39.7 |
| Released | 2025-04-16 | — |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 63 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1408 | 1339 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Step 1o Turbo 202506: —
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1335 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.86 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1426 | 1318 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1402 | 1308 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
Multimodal o3 leads
o3: 41.4 (#36), Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | 1214 | 1186 |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1401 | 1313 |
| LMArena Chinese | 1437 | 1380 |
| LMArena German | 1420 | 1314 |
| LMArena Russian | 1406 | 1327 |
| LMArena French | 1430 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
| LMArena Spanish | 1395 | — |
Instruction Following o3 leads
o3: 72.8 (#127), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1368 | 1310 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1372 | 1348 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | o3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1410 | 1336 |
| LMArena Creative Writing | 1359 | 1307 |
| LMArena Multi-Turn | 1405 | 1340 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Step 1o Turbo 202506?
o3 is the stronger model overall, scoring 47.5 to 39.7 on the Noometry Index.
Is o3 or Step 1o Turbo 202506 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 39.2 in the Noometry coding category.
How many benchmarks do o3 and Step 1o Turbo 202506 share?
14 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Step 1o Turbo 202506 has 14.