# Claude 3 Haiku vs Gemma 3n E4b IT

> Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-gemma-3n-e4b-it
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemma 3n E4b IT in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 3n E4b IT leads 35.1 to 9.8.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 25.9 | 37.3 |
| Rank | 340 | 206 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Gemma 3n E4b IT: 37.0 (#198)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1199 | 1268 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Gemma 3n E4b IT: 19.9 (#247)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 31.5% |
| LMArena Hard Prompts | 1174 | 1284 |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Gemma 3n E4b IT: 35.1 (#188)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1188 | 1251 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Gemma 3n E4b IT: 34.2 (#198)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1148 | 1246 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Gemma 3n E4b IT: —

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Gemma 3n E4b IT: 43.4 (#183)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1178 | 1285 |
| LMArena Chinese | 1155 | 1309 |
| LMArena French | 1195 | 1330 |
| LMArena German | 1174 | 1311 |
| LMArena Japanese | 1102 | 1272 |
| LMArena Korean | 1109 | 1259 |
| LMArena Russian | 1204 | 1288 |
| LMArena Spanish | 1166 | 1305 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Gemma 3n E4b IT: 66.1 (#210)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1173 | 1255 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Gemma 3n E4b IT: 38.7 (#191)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1190 | 1276 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Gemma 3n E4b IT: 50.1 (#186)

| Benchmark | Claude 3 Haiku | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1195 | 1306 |
| LMArena Creative Writing | 1157 | 1287 |
| LMArena Multi-Turn | 1190 | 1276 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Gemma 3n E4b IT?

Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Gemma 3n E4b IT better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Gemma 3n E4b IT share?

18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 3n E4b IT has 18.