# Gemma 2 2b IT vs Kimi K3

> Kimi K3 is the stronger model overall, scoring 59.5 to 33.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-2b-it-vs-kimi-k3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 0 categories and Kimi K3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 21.4.

## Snapshot

| | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| Provider | Google | Moonshot AI |
| Noometry Index | 33.1 | 59.5 |
| Rank | 248 | 15 |
| Context | — | 1.05M |
| Input $/M | — | $3 |
| Output $/M | — | $15 |
| Weights | Open | Open |

## Coding

- Gemma 2 2b IT: 32.3 (#273)
- Kimi K3: 61.0 (#10)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Coding | 1112 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| ALE-Bench | — | 1,524 |

## Agentic & Tool Use

- Gemma 2 2b IT: —
- Kimi K3: 41.8 (#20)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |

## Reasoning

- Gemma 2 2b IT: 21.4 (#224)
- Kimi K3: 63.0 (#17)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |

## Math

- Gemma 2 2b IT: 32.6 (#212)
- Kimi K3: 74.2 (#16)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Math | 1135 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |

## Knowledge

- Gemma 2 2b IT: 29.9 (#231)
- Kimi K3: 63.2 (#21)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Expert | 1096 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |

## Multimodal

- Gemma 2 2b IT: —
- Kimi K3: 37.8 (#70)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |

## Multilingual

- Gemma 2 2b IT: 32.3 (#257)
- Kimi K3: 56.3 (#21)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1121 | 1466 |
| LMArena Chinese | 1132 | 1529 |
| LMArena French | 1157 | 1491 |
| LMArena German | 1114 | 1488 |
| LMArena Japanese | 1083 | 1487 |
| LMArena Korean | 1055 | 1458 |
| LMArena Russian | 1118 | 1482 |
| LMArena Spanish | 1140 | 1472 |

## Instruction Following

- Gemma 2 2b IT: 57.8 (#263)
- Kimi K3: 77.7 (#14)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1118 | 1483 |

## Long Context

- Gemma 2 2b IT: 34.3 (#250)
- Kimi K3: 45.8 (#29)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1130 | 1494 |

## Writing & Preference

- Gemma 2 2b IT: 36.5 (#263)
- Kimi K3: 76.6 (#4)

| Benchmark | Gemma 2 2b IT | Kimi K3 |
|---|---|---|
| LMArena Text | 1156 | 1476 |
| LMArena Creative Writing | 1147 | 1454 |
| LMArena Multi-Turn | 1118 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |

## FAQ

### Is Gemma 2 2b IT better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 33.1 on the Noometry Index.

### Is Gemma 2 2b IT or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 32.3 in the Noometry coding category.

### How many benchmarks do Gemma 2 2b IT and Kimi K3 share?

17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Kimi K3 has 53.
