Model comparison
GPT-4.5 vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 37.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Step 3.5 Flash in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 32.6.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 37.2 | 42.3 |
| Released | 2025-02-27 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 42 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.5: 42.2 (#109), Step 3.5 Flash: 42.4 (#105)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1396 | 1436 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Step 3.5 Flash: —
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Step 3.5 Flash leads
GPT-4.5: 13.9 (#330), Step 3.5 Flash: 22.2 (#202)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1411 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 28.4% |
| 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 3.5 Flash leads
GPT-4.5: 32.6 (#211), Step 3.5 Flash: 42.6 (#84)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1412 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Step 3.5 Flash leads
GPT-4.5: 32.5 (#211), Step 3.5 Flash: 39.6 (#132)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1394 | 1421 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Step 3.5 Flash: —
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Step 3.5 Flash: 50.5 (#119)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1413 | 1385 |
| LMArena Chinese | 1421 | 1447 |
| LMArena French | 1418 | 1421 |
| LMArena German | 1457 | 1405 |
| LMArena Japanese | 1416 | 1354 |
| LMArena Korean | 1392 | 1352 |
| LMArena Russian | 1419 | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Too close to call
GPT-4.5: 72.6 (#134), Step 3.5 Flash: 73.1 (#124)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1404 | 1385 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Step 3.5 Flash leads
GPT-4.5: 40.4 (#155), Step 3.5 Flash: 42.8 (#117)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1406 | 1402 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Step 3.5 Flash leads
GPT-4.5: 56.9 (#134), Step 3.5 Flash: 58.8 (#113)
| Benchmark | GPT-4.5 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1417 | 1403 |
| LMArena Creative Writing | 1394 | 1357 |
| LMArena Multi-Turn | 1444 | 1405 |
| 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 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 37.2 on the Noometry Index.
Is GPT-4.5 or Step 3.5 Flash better for coding?
They score almost the same on coding (42.2 vs 42.4); test both on your own repository before choosing.
How many benchmarks do GPT-4.5 and Step 3.5 Flash share?
16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Step 3.5 Flash has 19.