# Gemini 2.5 Flash-Lite vs Grok-3 mini

> Grok-3 mini is the stronger model overall, scoring 41.0 to 36.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-grok-3-mini
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 3 categories and Grok-3 mini in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 32.1.
- The biggest single-benchmark swing is GPQA (HELM): 30.9% for Gemini 2.5 Flash-Lite and 67.5% for Grok-3 mini.

## Snapshot

| | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 36.4 | 41.0 |
| Rank | 208 | 130 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Grok-3 mini: 40.4 (#126)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| WeirdML | 35.2% | 42.6% |
| LMArena Coding | 1373 | 1380 |
| Aider Polyglot | — | 49.3% |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Grok-3 mini: —

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

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Grok-3 mini: 13.8 (#323)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 61.3% |
| LMArena Hard Prompts | 1377 | 1374 |
| Epoch Capabilities Index | 133.93 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| ARC-AGI-1 | — | 16.5% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Grok-3 mini: 40.3 (#78)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| Omni-MATH | 48% | 31.8% |
| LMArena Math | 1373 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Grok-3 mini: 46.3 (#75)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| MMLU-Pro | 53.7% | 79.9% |
| GPQA (HELM) | 30.9% | 67.5% |
| LMArena Expert | 1373 | 1395 |
| GPQA Diamond | — | 76.3% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 3.3% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Grok-3 mini: —

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Grok-3 mini: 48.3 (#141)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1369 | 1352 |
| LMArena Chinese | 1404 | 1387 |
| LMArena French | 1388 | 1357 |
| LMArena German | 1390 | 1350 |
| LMArena Japanese | 1359 | 1343 |
| LMArena Korean | 1358 | 1336 |
| LMArena Russian | 1373 | 1352 |
| LMArena Spanish | 1396 | 1379 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Grok-3 mini: 78.7 (#8)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| IFEval | 81% | 95.1% |
| LMArena Instruction Following | 1366 | 1356 |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Grok-3 mini: 41.0 (#142)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 47.2% | 66.7% |
| LMArena Longer Query | 1373 | 1372 |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Grok-3 mini: 52.7 (#163)

| Benchmark | Gemini 2.5 Flash-Lite | Grok-3 mini |
|---|---|---|
| LMArena Text | 1379 | 1370 |
| LMArena Creative Writing | 1366 | 1342 |
| WildBench | 81.8% | 65.1% |
| LMArena Multi-Turn | 1367 | 1355 |
| Short-Story Creative Writing | — | 73.5% |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 36.4 on the Noometry Index.

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

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 38.0 in the Noometry coding category.

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

26 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Grok-3 mini has 35.