# Gemini 2.5 Flash-Lite vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-step-3
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 3 categories and Step 3 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Step 3 leads 40.3 to 33.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 40.5% for Gemini 2.5 Flash-Lite and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 37.0 | 40.5 |
| Rank | 211 | 149 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.5 (#173)
- Step 3: 40.1 (#147)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Coding | 1373 | 1367 |
| WeirdML | 35.2% | — |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 28.0 (#96)
- Step 3: —

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |

## Reasoning

- Gemini 2.5 Flash-Lite: 22.2 (#205)
- Step 3: 28.4 (#105)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 62.3% |
| LMArena Hard Prompts | 1377 | 1355 |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Epoch Capabilities Index | 133.94 | — |

## Math

- Gemini 2.5 Flash-Lite: 38.0 (#144)
- Step 3: 37.6 (#148)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Math | 1373 | 1366 |
| Omni-MATH | 48% | — |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.5 (#210)
- Step 3: 36.8 (#164)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Expert | 1373 | 1333 |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 29.1 (#114)
- Step 3: 35.5 (#86)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Vision | 1198 | 1177 |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.3 (#134)
- Step 3: 46.3 (#159)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Non-English | 1369 | 1327 |
| LMArena Chinese | 1404 | 1397 |
| LMArena German | 1389 | 1371 |
| LMArena Korean | 1360 | 1269 |
| LMArena Russian | 1373 | 1331 |
| LMArena Spanish | 1396 | 1371 |
| LMArena French | 1388 | — |
| LMArena Japanese | 1359 | — |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.0 (#168)
- Step 3: 70.4 (#164)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1332 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#262)
- Step 3: 40.3 (#157)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Longer Query | 1373 | 1326 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 56.8 (#135)
- Step 3: 54.3 (#151)

| Benchmark | Gemini 2.5 Flash-Lite | Step 3 |
|---|---|---|
| LMArena Text | 1379 | 1350 |
| LMArena Creative Writing | 1367 | 1321 |
| LMArena Multi-Turn | 1366 | 1341 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 37.0 on the Noometry Index.

### Is Gemini 2.5 Flash-Lite or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 38.5 in the Noometry coding category.

### How many benchmarks do Gemini 2.5 Flash-Lite and Step 3 share?

17 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Step 3 has 17.