Model comparison
GPT-3.5-turbo vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 23.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 6.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 23.2 | 40.5 |
| Released | 2023-03-01 | — |
| Weights | Proprietary | Open |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
GPT-3.5-turbo: 23.9 (#331), Step 3: 40.1 (#147)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Coding | 1136 | 1367 |
| 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 3: —
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Step 3 leads
GPT-3.5-turbo: 13.8 (#332), Step 3: 28.4 (#105)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| 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 3 leads
GPT-3.5-turbo: 6.3 (#327), Step 3: 37.6 (#148)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Math | 1142 | 1366 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Step 3 leads
GPT-3.5-turbo: 10.0 (#303), Step 3: 36.8 (#164)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Expert | 1070 | 1333 |
| 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 3: 35.5 (#86)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
GPT-3.5-turbo: 31.5 (#258), Step 3: 46.3 (#159)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Non-English | 1108 | 1327 |
| LMArena Chinese | 1075 | 1397 |
| LMArena German | 1090 | 1371 |
| LMArena Korean | 1019 | 1269 |
| LMArena Russian | 1123 | 1331 |
| LMArena Spanish | 1121 | 1371 |
| LMArena French | 1118 | — |
| LMArena Japanese | 1043 | — |
Instruction Following Step 3 leads
GPT-3.5-turbo: 57.9 (#262), Step 3: 70.4 (#164)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1119 | 1332 |
Long Context Step 3 leads
GPT-3.5-turbo: 34.0 (#254), Step 3: 40.3 (#157)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Longer Query | 1121 | 1326 |
Writing & Preference Step 3 leads
GPT-3.5-turbo: 25.3 (#305), Step 3: 54.3 (#151)
| Benchmark | GPT-3.5-turbo | Step 3 |
|---|---|---|
| LMArena Text | 1125 | 1350 |
| LMArena Creative Writing | 1092 | 1321 |
| LMArena Multi-Turn | 1117 | 1341 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 23.2 on the Noometry Index.
Is GPT-3.5-turbo or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 23.9 in the Noometry coding category.
How many benchmarks do GPT-3.5-turbo and Step 3 share?
15 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Step 3 has 17.