# Gemma 3 4B vs Kimi K2 Thinking Turbo

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-kimi-k2-thinking-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 83.1% for Kimi K2 Thinking Turbo.

## Snapshot

| | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| Provider | Google | Moonshot AI |
| Noometry Index | 27.9 | 45.4 |
| Rank | 320 | 63 |
| Context | 131K | — |
| Input $/M | $0.04 | — |
| Output $/M | $0.08 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.3 (#214)
- Kimi K2 Thinking Turbo: 38.1 (#166)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1230 | 1454 |
| LMArena WebDev | — | 1322 |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- Kimi K2 Thinking Turbo: —

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- Kimi K2 Thinking Turbo: 31.4 (#72)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 0% | 20% |
| LMArena Hard Prompts | 1253 | 1428 |
| Kagi LLM Benchmark | 25.2% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |

## Math

- Gemma 3 4B: 15.8 (#286)
- Kimi K2 Thinking Turbo: 45.5 (#62)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 83.1% |
| LMArena Math | 1239 | 1429 |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- Kimi K2 Thinking Turbo: 50.9 (#64)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 23.2% | 84.2% |
| LMArena Expert | 1223 | 1439 |
| Vectara Hallucination Rate | 6.4% | — |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- Kimi K2 Thinking Turbo: 51.6 (#104)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1273 | 1398 |
| LMArena German | 1281 | 1390 |
| LMArena Russian | 1294 | 1390 |
| LMArena Chinese | — | 1457 |
| LMArena French | — | 1425 |
| LMArena Japanese | — | 1356 |
| LMArena Korean | — | 1329 |
| LMArena Spanish | — | 1407 |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- Kimi K2 Thinking Turbo: 74.2 (#103)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1239 | 1403 |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- Kimi K2 Thinking Turbo: 43.2 (#99)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1274 | 1415 |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- Kimi K2 Thinking Turbo: 60.2 (#99)

| Benchmark | Gemma 3 4B | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1291 | 1415 |
| LMArena Creative Writing | 1270 | 1373 |
| LMArena Multi-Turn | 1255 | 1414 |
| EQ-Bench Creative Writing | 1068 | — |

## FAQ

### Is Gemma 3 4B better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 27.9 on the Noometry Index.

### Is Gemma 3 4B or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 35.3 in the Noometry coding category.

### How many benchmarks do Gemma 3 4B and Kimi K2 Thinking Turbo share?

15 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Kimi K2 Thinking Turbo has 21.