# Gemma 3 4B vs Kimi K2.7 Code

> Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 27.9 on the Noometry Index. Gemma 3 4B costs 34× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-kimi-k2-7-code
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Kimi K2.7 Code in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.7 Code leads 53.6 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 95.6% for Kimi K2.7 Code.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 131K.

## Snapshot

| | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| Provider | Google | Moonshot AI |
| Noometry Index | 27.9 | 43.0 |
| Rank | 320 | 90 |
| Context | 131K | 262K |
| Input $/M | $0.04 | $0.95 |
| Output $/M | $0.08 | $4 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.3 (#214)
- Kimi K2.7 Code: 42.4 (#92)

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | — | 30.5% |
| FrontierCode | — | 30.1% |
| LMArena WebDev | — | 1473 |
| SciCode | — | 47.5% |
| WeirdML | — | 54.1% |
| LMArena Coding | 1230 | — |
| ALE-Bench | — | 886.23 |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- Kimi K2.7 Code: 23.9 (#115)

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | — | 37.6% |
| Berkeley Function Calling Leaderboard | 19.6% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 5,083 |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- Kimi K2.7 Code: 38.2 (#56)

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| Epoch Capabilities Index | 116.02 | 150.01 |
| SimpleBench | — | 57.9% |
| Kagi LLM Benchmark | 25.2% | — |
| CritPt | — | 10% |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Surface Evolver Bench | — | 48.8% |

## Math

- Gemma 3 4B: 15.8 (#286)
- Kimi K2.7 Code: 52.6 (#39)

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 54% |
| FrontierMath Tier 4 | — | 12.2% |
| LMArena Math | 1239 | — |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- Kimi K2.7 Code: 53.6 (#51)

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 23.2% | 87.9% |
| SimpleQA Verified | — | 36.5% |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- Kimi K2.7 Code: —

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- Kimi K2.7 Code: —

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| LMArena Instruction Following | 1239 | — |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- Kimi K2.7 Code: —

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| LMArena Longer Query | 1274 | — |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- Kimi K2.7 Code: —

| Benchmark | Gemma 3 4B | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1270 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |

## FAQ

### Is Gemma 3 4B better than Kimi K2.7 Code?

Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 27.9 on the Noometry Index. Gemma 3 4B costs 34× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or Kimi K2.7 Code?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

### Is Gemma 3 4B or Kimi K2.7 Code better for coding?

Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 35.3 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.7 Code does, with 262K tokens against 131K.

### How many benchmarks do Gemma 3 4B and Kimi K2.7 Code share?

4 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Kimi K2.7 Code has 19.