Model comparison
GPT-4 Turbo vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 30.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 14.9.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
Side by side
| GPT-4 Turbo | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 30.3 | 43.8 |
| Released | 2023-11-06 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 4K | 66K |
| Input $ / M tokens | $10 | $1 |
| Output $ / M tokens | $30 | $2.70 |
| Results tracked | 36 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
GPT-4 Turbo: 33.4 (#247), Step 5 Preview: 50.6 (#40)
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Step 5 Preview leads
GPT-4 Turbo: 14.9 (#311), Step 5 Preview: 38.0 (#58)
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| SimpleBench | 25.1% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Not comparable
GPT-4 Turbo: 8.6 (#316), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |
Knowledge Not comparable
GPT-4 Turbo: 24.3 (#263), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.0 (#104), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.7 (#211), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1275 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 66.0 (#211), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1250 | — |
Long Context Not comparable
GPT-4 Turbo: 38.0 (#200), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1254 | — |
Writing & Preference Not comparable
GPT-4 Turbo: 47.9 (#201), Step 5 Preview: —
| Benchmark | GPT-4 Turbo | Step 5 Preview |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 30.3 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 128K.
How many benchmarks do GPT-4 Turbo and Step 5 Preview share?
0 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Step 5 Preview has 3.