Model comparison
Gemini 1.5 Flash (May 2024) vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 32.9 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 34.9 to 20.8.
- 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 | 32.9 | 39.9 |
| 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): 33.9 (#233), Step 3: 39.5 (#144)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Coding | 1262 | 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): 26.3 (#97), Step 3: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning Step 3 leads
Gemini 1.5 Flash (May 2024): 20.8 (#212), Step 3: 27.6 (#102)
| 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 | 129.37 | — |
| ForecastBench | 53.9 | — |
| PIQA | 87.5% | — |
Math Step 3 leads
Gemini 1.5 Flash (May 2024): 20.8 (#274), Step 3: 34.9 (#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 (#253), Step 3: 36.2 (#161)
| 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): 35.3 (#76), Step 3: 34.9 (#81)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Vision | 1141 | 1176 |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Step 3 leads
Gemini 1.5 Flash (May 2024): 43.1 (#184), Step 3: 46.5 (#154)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Non-English | 1278 | 1327 |
| LMArena Chinese | 1295 | 1396 |
| LMArena German | 1262 | 1371 |
| LMArena Korean | 1220 | 1271 |
| LMArena Russian | 1288 | 1331 |
| LMArena Spanish | 1242 | 1372 |
| LMArena French | 1257 | — |
| LMArena Japanese | 1252 | — |
Instruction Following Step 3 leads
Gemini 1.5 Flash (May 2024): 67.0 (#199), Step 3: 70.6 (#159)
| 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 (#182), Step 3: 40.3 (#152)
| 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): 48.9 (#190), Step 3: 54.5 (#146)
| Benchmark | Gemini 1.5 Flash (May 2024) | Step 3 |
|---|---|---|
| LMArena Text | 1287 | 1351 |
| LMArena Creative Writing | 1285 | 1322 |
| LMArena Multi-Turn | 1253 | 1340 |
| 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 39.9 to 32.9 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 33.9 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.