Model comparison
Gemini 1.0 Pro vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 27.3 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
StepFunSummary
- They share 14 benchmarks with published results for both. Gemini 1.0 Pro 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 9.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 27.3 | 40.5 |
| Released | 2023-12-13 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemini 1.0 Pro: 32.2 (#275), Step 3: 40.1 (#147)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Coding | 1108 | 1367 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Step 3 leads
Gemini 1.0 Pro: 17.1 (#296), Step 3: 28.4 (#105)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 117.04 | — |
Math Step 3 leads
Gemini 1.0 Pro: 9.3 (#321), Step 3: 37.6 (#148)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Math | 1132 | 1366 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
Knowledge Step 3 leads
Gemini 1.0 Pro: 15.6 (#291), Step 3: 36.8 (#164)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Expert | 1059 | 1333 |
| GPQA Diamond | 34% | — |
| MMLU | 70% | — |
Multimodal Not comparable
Gemini 1.0 Pro: —, Step 3: 35.5 (#86)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Gemini 1.0 Pro: 33.4 (#252), Step 3: 46.3 (#159)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Non-English | 1138 | 1327 |
| LMArena Chinese | 1124 | 1397 |
| LMArena German | 1125 | 1371 |
| LMArena Russian | 1186 | 1331 |
| LMArena Spanish | 1119 | 1371 |
| LMArena French | 1145 | — |
| LMArena Japanese | 1023 | — |
| LMArena Korean | — | 1269 |
Instruction Following Step 3 leads
Gemini 1.0 Pro: 57.6 (#267), Step 3: 70.4 (#164)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1332 |
Long Context Step 3 leads
Gemini 1.0 Pro: 34.3 (#249), Step 3: 40.3 (#157)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Longer Query | 1132 | 1326 |
Writing & Preference Step 3 leads
Gemini 1.0 Pro: 36.0 (#264), Step 3: 54.3 (#151)
| Benchmark | Gemini 1.0 Pro | Step 3 |
|---|---|---|
| LMArena Text | 1149 | 1350 |
| LMArena Creative Writing | 1131 | 1321 |
| LMArena Multi-Turn | 1139 | 1341 |
Frequently asked questions
Is Gemini 1.0 Pro better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Step 3 share?
14 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Step 3 has 17.