# Gemini 3.5 Flash Lite vs GPT-5.4

> GPT-5.4 is the stronger model overall, scoring 59.5 to 41.8 on the Noometry Index. Gemini 3.5 Flash Lite costs 6.6× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-lite-vs-gpt-5-4
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 0 categories and GPT-5.4 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 leads 73.3 to 25.7.
- The biggest single-benchmark swing is ARC-AGI-2: 10.3% for Gemini 3.5 Flash Lite and 74% for GPT-5.4.
- Gemini 3.5 Flash Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $2.50 / $15 for GPT-5.4.
- GPT-5.4 accepts more context: 1.05M tokens versus 1.05M.

## Snapshot

| | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 41.8 | 59.5 |
| Rank | 113 | 14 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.30 | $2.50 |
| Output $/M | $2.50 | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.5 Flash Lite: 42.1 (#96)
- GPT-5.4: 52.8 (#28)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena WebDev | 1440 | 1465 |
| SciCode | 41.3% | 56.6% |
| WeirdML | 39% | 77.7% |
| LMArena Coding | 1455 | 1497 |
| ALE-Bench | 765.27 | 1,607 |
| SWE-bench Verified | — | 76.9% |
| DeepSWE | — | 51.8% |
| GSO | — | 31.4% |
| MirrorCode | — | 15.6% |
| AlgoTune | — | 1.85 |

## Agentic & Tool Use

- Gemini 3.5 Flash Lite: 28.6 (#82)
- GPT-5.4: 46.5 (#12)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| Terminal-Bench | — | 81.8% |
| APEX-Agents | — | 52.4% |
| τ²-bench Banking | — | 39.4% |
| DeepResearch Bench | — | 35.1% |
| PostTrainBench | — | 19% |
| GBAEval | — | 45.1% |
| GDP.pdf | 10% | — |
| LMArena Search | — | 1197 |
| METR Time Horizons | — | 74.3% |
| Vending-Bench 2 | — | 6,144 |

## Reasoning

- Gemini 3.5 Flash Lite: 27.8 (#95)
- GPT-5.4: 61.7 (#17)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| ARC-AGI-2 | 10.3% | 74% |
| NYT Connections (extended) | 60.4% | 91.3% |
| ARC-AGI-1 | 53.5% | 93.7% |
| CritPt | 0% | 23.4% |
| Chess Puzzles | 22% | 44% |
| LMArena Hard Prompts | 1441 | 1485 |
| Mystery Game Puzzles | 19% | 37% |
| DTBench | 83.5% | 94.4% |
| LMCA | 37.6% | 52% |
| Epoch Capabilities Index | 145.12 | 156.92 |
| Kagi LLM Benchmark | — | 63.8% |
| EnigmaEval | — | 16% |
| Thematic Generalization | — | 80% |
| EBR-Bench | — | 25.4% |
| ForecastBench | — | 59.5 |

## Math

- Gemini 3.5 Flash Lite: 25.7 (#245)
- GPT-5.4: 73.3 (#14)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 26% | 78.6% |
| FrontierMath Tier 4 | 0% | 49% |
| OTIS Mock AIME 2024-2025 | 71.1% | 97.8% |
| ProofBench | 13% | 56% |
| LMArena Math | 1431 | 1488 |
| MathArena Final-Answer Competitions | — | 83.1% |
| FrontierMath (Feb 2025 set) | — | 47.6% |
| FrontierMath Tier 4 (v1) | — | 27.1% |

## Knowledge

- Gemini 3.5 Flash Lite: 50.0 (#66)
- GPT-5.4: 65.3 (#13)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| GPQA Diamond | 83.3% | 93.3% |
| LMArena Expert | 1430 | 1507 |
| Humanity's Last Exam | — | 36.2% |
| SimpleQA Verified | — | 45.1% |
| Vectara Hallucination Rate | — | 7% |

## Multimodal

- Gemini 3.5 Flash Lite: 40.3 (#38)
- GPT-5.4: 43.8 (#19)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena Vision | 1266 | 1302 |
| Blueprint-Bench 2 | — | 27.1% |
| Furniture Assembly | — | 37.5% |
| LMArena Document | — | 1471 |

## Multilingual

- Gemini 3.5 Flash Lite: 53.8 (#59)
- GPT-5.4: 56.4 (#22)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena Non-English | 1428 | 1465 |
| LMArena Chinese | 1467 | 1520 |
| LMArena French | 1452 | 1493 |
| LMArena German | 1454 | 1472 |
| LMArena Japanese | 1428 | 1484 |
| LMArena Korean | 1406 | 1449 |
| LMArena Russian | 1443 | 1480 |
| LMArena Spanish | 1440 | 1453 |

## Instruction Following

- Gemini 3.5 Flash Lite: 75.0 (#77)
- GPT-5.4: 77.3 (#25)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1469 |

## Long Context

- Gemini 3.5 Flash Lite: 43.8 (#80)
- GPT-5.4: 50.3 (#8)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena Longer Query | 1435 | 1474 |
| CL-bench | — | 27.9% |
| CL-bench Life | — | 21.7% |

## Writing & Preference

- Gemini 3.5 Flash Lite: 64.4 (#55)
- GPT-5.4: 72.1 (#18)

| Benchmark | Gemini 3.5 Flash Lite | GPT-5.4 |
|---|---|---|
| LMArena Text | 1436 | 1469 |
| LMArena Creative Writing | 1419 | 1439 |
| EQ-Bench Creative Writing | 1559 | 1840 |
| LMArena Multi-Turn | 1445 | 1482 |
| EQ-Bench 4 | — | 1272 |

## FAQ

### Is Gemini 3.5 Flash Lite better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.5 to 41.8 on the Noometry Index. Gemini 3.5 Flash Lite costs 6.6× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.5 Flash Lite or GPT-5.4?

Gemini 3.5 Flash Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.4 lists at $2.50 and $15.

### Is Gemini 3.5 Flash Lite or GPT-5.4 better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.8 versus 42.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 does, with 1.05M tokens against 1.05M.

### How many benchmarks do Gemini 3.5 Flash Lite and GPT-5.4 share?

37 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 38 scored results on Noometry and GPT-5.4 has 68.