Model comparison
Gemini 3.5 Flash Lite vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 1.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Google
StepFunSummary
- They share 18 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 3 categories and Step 5 Preview in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 25.9.
- The biggest single-benchmark swing is ProofBench: 13% for Gemini 3.5 Flash Lite and 42% for Step 5 Preview.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Gemini 3.5 Flash Lite accepts more context: 1.05M tokens versus 1.02M.
Side by side
| Gemini 3.5 Flash Lite | Step 5 Preview | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 41.5 | 47.9 |
| Released | 2026-07-21 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $1 |
| Output $ / M tokens | $2.50 | $2.70 |
| Results tracked | 39 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Gemini 3.5 Flash Lite: 42.4 (#104), Step 5 Preview: 51.8 (#36)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1440 | 1564 |
| SciCode | 41.3% | 58.9% |
| LMArena Coding | 1453 | 1480 |
| WeirdML | 39% | — |
| ALE-Bench | 765.27 | — |
Agentic & Tool Use Not comparable
Gemini 3.5 Flash Lite: 25.7 (#107), Step 5 Preview: —
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| APEX-Agents | 29.3% | — |
| GDP.pdf | 10% | — |
Reasoning Step 5 Preview leads
Gemini 3.5 Flash Lite: 27.8 (#114), Step 5 Preview: 40.0 (#57)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| LMArena Hard Prompts | 1441 | 1465 |
| ARC-AGI-2 | 10.3% | — |
| NYT Connections (extended) | 60.4% | — |
| ARC-AGI-1 | 53.5% | — |
| Chess Puzzles | 22% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 145.13 | — |
Math Step 5 Preview leads
Gemini 3.5 Flash Lite: 25.9 (#264), Step 5 Preview: 46.1 (#72)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| ProofBench | 13% | 42% |
| LMArena Math | 1433 | 1470 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
Knowledge Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 50.1 (#72), Step 5 Preview: 41.2 (#112)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1435 | 1470 |
| GPQA Diamond | 83.3% | — |
Multimodal Too close to call
Gemini 3.5 Flash Lite: 41.1 (#40), Step 5 Preview: 41.0 (#41)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1268 | 1267 |
Multilingual Too close to call
Gemini 3.5 Flash Lite: 53.5 (#63), Step 5 Preview: 53.8 (#54)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1427 | 1432 |
| LMArena Chinese | 1469 | 1519 |
| LMArena Russian | 1443 | 1436 |
| LMArena Spanish | 1442 | 1439 |
| LMArena French | 1451 | — |
| LMArena German | 1454 | — |
| LMArena Japanese | 1427 | — |
| LMArena Korean | 1407 | — |
Instruction Following Step 5 Preview leads
Gemini 3.5 Flash Lite: 74.8 (#85), Step 5 Preview: 76.0 (#50)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1420 | 1444 |
Long Context Too close to call
Gemini 3.5 Flash Lite: 43.9 (#84), Step 5 Preview: 44.5 (#64)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1435 | 1455 |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.2 (#57), Step 5 Preview: 62.8 (#71)
| Benchmark | Gemini 3.5 Flash Lite | Step 5 Preview |
|---|---|---|
| LMArena Text | 1435 | 1442 |
| LMArena Creative Writing | 1420 | 1410 |
| LMArena Multi-Turn | 1445 | 1447 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 41.5 on the Noometry Index. Gemini 3.5 Flash Lite costs 1.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.5 Flash Lite or Step 5 Preview?
Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Gemini 3.5 Flash Lite or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.5 Flash Lite does, with 1.05M tokens against 1.02M.
How many benchmarks do Gemini 3.5 Flash Lite and Step 5 Preview share?
18 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 39 scored results on Noometry and Step 5 Preview has 18.