Model comparison
Gemini 1.5 Flash (May 2024) vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 33.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
StepFunSummary
- They share 16 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 1 category 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 22.1.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 33.2 | 40.5 |
| Released | 2024-05-14 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemini 1.5 Flash (May 2024): 34.4 (#236), Step 3: 40.1 (#147)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Coding | 1261 | 1367 |
| WeirdML | 24.9% | — |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash (May 2024): 26.6 (#102), Step 3: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning Step 3 leads
Gemini 1.5 Flash (May 2024): 21.7 (#215), Step 3: 28.4 (#105)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| DTBench | 53.8% | — |
| Epoch Capabilities Index | 129.36 | — |
| ForecastBench | 53.9 | — |
| PIQA | 87.5% | — |
Math Step 3 leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), Step 3: 37.6 (#148)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Math | 1269 | 1366 |
| OTIS Mock AIME 2024-2025 | 16.3% | — |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge Step 3 leads
Gemini 1.5 Flash (May 2024): 26.2 (#260), Step 3: 36.8 (#164)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Expert | 1233 | 1333 |
| GPQA Diamond | 47.3% | — |
| MMLU-Pro | 67.8% | — |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Too close to call
Gemini 1.5 Flash (May 2024): 36.0 (#81), Step 3: 35.5 (#86)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Vision | 1141 | 1177 |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Step 3 leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), Step 3: 46.3 (#159)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Non-English | 1278 | 1327 |
| LMArena Chinese | 1295 | 1397 |
| LMArena German | 1262 | 1371 |
| LMArena Korean | 1221 | 1269 |
| LMArena Russian | 1288 | 1331 |
| LMArena Spanish | 1243 | 1371 |
| LMArena French | 1258 | — |
| LMArena Japanese | 1252 | — |
Instruction Following Step 3 leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), Step 3: 70.4 (#164)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1332 |
| IFEval | 83.1% | — |
Long Context Step 3 leads
Gemini 1.5 Flash (May 2024): 39.0 (#187), Step 3: 40.3 (#157)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Longer Query | 1284 | 1326 |
Writing & Preference Step 3 leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), Step 3: 54.3 (#151)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Text | 1287 | 1350 |
| LMArena Creative Writing | 1285 | 1321 |
| LMArena Multi-Turn | 1253 | 1341 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 33.2 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Step 3 share?
16 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Step 3 has 17.