# Claude Haiku 4.5 vs Gemma 3n E4b IT

> Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 27× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-gemma-3n-e4b-it
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemma 3n E4b IT in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 43.0 to 32.5.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 33K.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.3 | 36.7 |
| Rank | 155 | 203 |
| Context | 200K | 33K |
| Input $/M | $1 | $0.06 |
| Output $/M | $5 | $0.12 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 43.9 (#71)
- Gemma 3n E4b IT: 36.4 (#193)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1454 | 1269 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.5 (#50)
- Gemma 3n E4b IT: —

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#310)
- Gemma 3n E4b IT: 19.2 (#239)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1284 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | — | 31.5% |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.42 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 43.0 (#69)
- Gemma 3n E4b IT: 32.5 (#186)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1395 | 1251 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.6 (#146)
- Gemma 3n E4b IT: 33.6 (#193)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1443 | 1245 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 27.0 (#111)
- Gemma 3n E4b IT: —

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 50.1 (#124)
- Gemma 3n E4b IT: 43.5 (#179)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1376 | 1285 |
| LMArena Chinese | 1415 | 1310 |
| LMArena French | 1408 | 1330 |
| LMArena German | 1377 | 1312 |
| LMArena Japanese | 1339 | 1274 |
| LMArena Korean | 1346 | 1259 |
| LMArena Russian | 1380 | 1288 |
| LMArena Spanish | 1420 | 1305 |

## Instruction Following

- Claude Haiku 4.5: 71.6 (#144)
- Gemma 3n E4b IT: 66.3 (#205)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1414 | 1255 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#86)
- Gemma 3n E4b IT: 38.8 (#185)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1427 | 1277 |

## Writing & Preference

- Claude Haiku 4.5: 58.1 (#119)
- Gemma 3n E4b IT: 50.3 (#181)

| Benchmark | Claude Haiku 4.5 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1396 | 1306 |
| LMArena Creative Writing | 1371 | 1287 |
| LMArena Multi-Turn | 1409 | 1276 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Gemma 3n E4b IT?

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 27× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Haiku 4.5 or Gemma 3n E4b IT?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

### Is Claude Haiku 4.5 or Gemma 3n E4b IT better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 36.4 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 4.5 does, with 200K tokens against 33K.

### How many benchmarks do Claude Haiku 4.5 and Gemma 3n E4b IT share?

17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemma 3n E4b IT has 18.