Model comparison
GPT-5.5 Instant vs Step 3
GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 39.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and Step 3 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 36.2.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.5 Instant | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.5 | 39.9 |
| Released | 2026-05-05 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
GPT-5.5 Instant: 43.7 (#73), Step 3: 39.5 (#144)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Coding | 1433 | 1367 |
| SciCode | 48.6% | — |
Reasoning Step 3 leads
GPT-5.5 Instant: 24.2 (#149), Step 3: 27.6 (#102)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Epoch Capabilities Index | 142.48 | — |
Math Step 3 leads
GPT-5.5 Instant: 26.1 (#241), Step 3: 34.9 (#148)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Math | 1420 | 1366 |
| FrontierMath (Tiers 1-3) | 26.3% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.1% | — |
Knowledge GPT-5.5 Instant leads
GPT-5.5 Instant: 48.9 (#68), Step 3: 36.2 (#161)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Expert | 1409 | 1333 |
| GPQA Diamond | 82.5% | — |
Multimodal GPT-5.5 Instant leads
GPT-5.5 Instant: 39.3 (#48), Step 3: 34.9 (#81)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Vision | 1250 | 1176 |
| LMArena Document | 1403 | — |
Multilingual GPT-5.5 Instant leads
GPT-5.5 Instant: 53.0 (#76), Step 3: 46.5 (#154)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Non-English | 1417 | 1327 |
| LMArena Chinese | 1457 | 1396 |
| LMArena German | 1410 | 1371 |
| LMArena Korean | 1393 | 1271 |
| LMArena Russian | 1430 | 1331 |
| LMArena Spanish | 1430 | 1372 |
| LMArena French | 1428 | — |
| LMArena Japanese | 1408 | — |
Instruction Following GPT-5.5 Instant leads
GPT-5.5 Instant: 74.4 (#94), Step 3: 70.6 (#159)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1407 | 1332 |
Long Context GPT-5.5 Instant leads
GPT-5.5 Instant: 43.4 (#92), Step 3: 40.3 (#152)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Longer Query | 1422 | 1326 |
Writing & Preference GPT-5.5 Instant leads
GPT-5.5 Instant: 62.0 (#81), Step 3: 54.5 (#146)
| Benchmark | GPT-5.5 Instant | Step 3 |
|---|---|---|
| LMArena Text | 1419 | 1351 |
| LMArena Creative Writing | 1420 | 1322 |
| LMArena Multi-Turn | 1434 | 1340 |
Frequently asked questions
Is GPT-5.5 Instant better than Step 3?
GPT-5.5 Instant is the stronger model overall, scoring 42.5 to 39.9 on the Noometry Index.
Is GPT-5.5 Instant or Step 3 better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 43.7 versus 39.5 in the Noometry coding category.
How many benchmarks do GPT-5.5 Instant and Step 3 share?
16 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Step 3 has 17.