# Gemini 2.0 Flash-Lite vs GPT-5 Mini

> GPT-5 Mini is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-0-flash-lite-vs-gpt-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and GPT-5 Mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 31.8.
- The biggest single-benchmark swing is Omni-MATH: 37.4% for Gemini 2.0 Flash-Lite and 72.2% for GPT-5 Mini.

## Snapshot

| | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 37.3 | 41.7 |
| Rank | 189 | 115 |
| Context | — | 400K |
| Input $/M | — | $0.25 |
| Output $/M | — | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.0 Flash-Lite: 37.4 (#181)
- GPT-5 Mini: 40.0 (#134)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1322 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |

## Agentic & Tool Use

- Gemini 2.0 Flash-Lite: —
- GPT-5 Mini: 31.0 (#64)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- Gemini 2.0 Flash-Lite: 21.2 (#203)
- GPT-5 Mini: 24.1 (#153)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1380 |
| DTBench | 52.5% | 80.5% |
| ForecastBench | 57.1 | 61 |
| ARC-AGI-2 | — | 4.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 10% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 34.2% |
| Epoch Capabilities Index | — | 145.51 |
| LiveBench | 54.3% | — |

## Math

- Gemini 2.0 Flash-Lite: 31.8 (#192)
- GPT-5 Mini: 46.3 (#59)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| Omni-MATH | 37.4% | 72.2% |
| LMArena Math | 1309 | 1377 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Gemini 2.0 Flash-Lite: 34.6 (#185)
- GPT-5 Mini: 45.5 (#80)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| MMLU-Pro | 72% | 83.5% |
| GPQA (HELM) | 50% | 75.6% |
| LMArena Expert | 1305 | 1377 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |

## Multimodal

- Gemini 2.0 Flash-Lite: 30.6 (#103)
- GPT-5 Mini: 35.0 (#80)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1100 | 1202 |
| VPCT | — | 40.2% |

## Multilingual

- Gemini 2.0 Flash-Lite: 46.2 (#156)
- GPT-5 Mini: 49.1 (#131)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1323 | 1363 |
| LMArena Chinese | 1339 | 1387 |
| LMArena French | 1346 | 1385 |
| LMArena German | 1306 | 1366 |
| LMArena Japanese | 1302 | 1342 |
| LMArena Korean | 1325 | 1306 |
| LMArena Russian | 1328 | 1362 |
| LMArena Spanish | 1313 | 1355 |

## Instruction Following

- Gemini 2.0 Flash-Lite: 70.6 (#158)
- GPT-5 Mini: 76.4 (#43)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| IFEval | 82.4% | 92.7% |
| LMArena Instruction Following | 1305 | 1357 |
| LiveBench Instruction Following | 78.3% | — |

## Long Context

- Gemini 2.0 Flash-Lite: 40.1 (#155)
- GPT-5 Mini: 41.9 (#127)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1321 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- Gemini 2.0 Flash-Lite: 51.9 (#172)
- GPT-5 Mini: 55.4 (#143)

| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1330 | 1373 |
| LMArena Creative Writing | 1319 | 1325 |
| WildBench | 79% | 85.5% |
| LMArena Multi-Turn | 1307 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| LiveBench Language | 34.3% | — |

## FAQ

### Is Gemini 2.0 Flash-Lite better than GPT-5 Mini?

GPT-5 Mini is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

### Is Gemini 2.0 Flash-Lite or GPT-5 Mini better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 37.4 in the Noometry coding category.

### How many benchmarks do Gemini 2.0 Flash-Lite and GPT-5 Mini share?

25 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and GPT-5 Mini has 60.