Model comparison
GPT-3.5-turbo vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
StepFunSummary
- They share 13 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 6.3.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 16K.
Side by side
| GPT-3.5-turbo | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 23.2 | 47.9 |
| Released | 2023-03-01 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 16K | 1.02M |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.50 | $1 |
| Output $ / M tokens | $1.50 | $2.70 |
| Results tracked | 44 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
GPT-3.5-turbo: 23.9 (#331), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1136 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Step 5 Preview: —
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Step 5 Preview leads
GPT-3.5-turbo: 13.8 (#332), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Step 5 Preview leads
GPT-3.5-turbo: 6.3 (#327), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Math | 1142 | 1470 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| ProofBench | — | 42% |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Step 5 Preview leads
GPT-3.5-turbo: 10.0 (#303), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1070 | 1470 |
| GPQA Diamond | 28% | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
GPT-3.5-turbo: 31.5 (#258), Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1108 | 1432 |
| LMArena Chinese | 1075 | 1519 |
| LMArena Russian | 1123 | 1436 |
| LMArena Spanish | 1121 | 1439 |
| LMArena French | 1118 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
Instruction Following Step 5 Preview leads
GPT-3.5-turbo: 57.9 (#262), Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1119 | 1444 |
Long Context Step 5 Preview leads
GPT-3.5-turbo: 34.0 (#254), Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1121 | 1455 |
Writing & Preference Step 5 Preview leads
GPT-3.5-turbo: 25.3 (#305), Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-3.5-turbo | Step 5 Preview |
|---|---|---|
| LMArena Text | 1125 | 1442 |
| LMArena Creative Writing | 1092 | 1410 |
| LMArena Multi-Turn | 1117 | 1447 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.9× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, GPT-3.5-turbo or Step 5 Preview?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is GPT-3.5-turbo or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Step 5 Preview share?
13 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Step 5 Preview has 18.