Model comparison
GPT-5.5 Pro vs Step 3
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 39.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in math, where GPT-5.5 Pro leads 83.8 to 34.9.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.5 Pro | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 64.3 | 39.9 |
| Released | 2026-04-23 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 14 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.5 Pro: —, Step 3: 39.5 (#144)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
Reasoning GPT-5.5 Pro leads
GPT-5.5 Pro: 73.6 (#7), Step 3: 27.6 (#102)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| SimpleBench | 76.9% | — |
| Kagi LLM Benchmark | — | 62.3% |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30.6% | — |
| Chess Puzzles | 64% | — |
| LMArena Hard Prompts | — | 1355 |
| DTBench | 96% | — |
| LMCA | 53.9% | — |
| Epoch Capabilities Index | 162.45 | — |
Math GPT-5.5 Pro leads
GPT-5.5 Pro: 83.8 (#8), Step 3: 34.9 (#148)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87.7% | — |
| FrontierMath Tier 4 | 78% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| LMArena Math | — | 1366 |
| FrontierMath (Feb 2025 set) | 52.4% | — |
| FrontierMath Tier 4 (v1) | 39.6% | — |
Knowledge GPT-5.5 Pro leads
GPT-5.5 Pro: 64.2 (#17), Step 3: 36.2 (#161)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| GPQA Diamond | 93.9% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
GPT-5.5 Pro: —, Step 3: 34.9 (#81)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
GPT-5.5 Pro: —, Step 3: 46.5 (#154)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
GPT-5.5 Pro: —, Step 3: 70.6 (#159)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
GPT-5.5 Pro: —, Step 3: 40.3 (#152)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
GPT-5.5 Pro: —, Step 3: 54.5 (#146)
| Benchmark | GPT-5.5 Pro | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is GPT-5.5 Pro better than Step 3?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 39.9 on the Noometry Index.
How many benchmarks do GPT-5.5 Pro and Step 3 share?
0 benchmarks have published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and Step 3 has 17.