# Claude Haiku 4.5 vs Gemma 7B

> Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-gemma-7b
- Last updated: 2026-10-12
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Gemma 7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Haiku 4.5 leads 57.9 to 27.1.
- Gemma 7B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.5 | 30.0 |
| Rank | 165 | 299 |
| Context | 200K | — |
| Input $/M | $1 | — |
| Output $/M | $5 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Gemma 7B: 30.5 (#294)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Coding | 1453 | 1048 |
| 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 | — |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Gemma 7B: —

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| 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 (#320)
- Gemma 7B: 19.9 (#249)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1042 |
| Epoch Capabilities Index | 142.41 | 111.99 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |

## Math

- Claude Haiku 4.5: 44.9 (#78)
- Gemma 7B: 31.2 (#228)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Math | 1396 | 1066 |
| 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% | — |
| GSM8K | — | 46.4% |

## Knowledge

- Claude Haiku 4.5: 37.7 (#153)
- Gemma 7B: 27.3 (#252)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Expert | 1442 | 1001 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Gemma 7B: —

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Gemma 7B: 25.1 (#287)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1377 | 999 |
| LMArena Chinese | 1417 | 1035 |
| LMArena French | 1408 | 1025 |
| LMArena Russian | 1381 | 993 |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Gemma 7B: 51.5 (#295)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1017 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Gemma 7B: 31.1 (#282)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1427 | 1022 |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Gemma 7B: 27.1 (#302)

| Benchmark | Claude Haiku 4.5 | Gemma 7B |
|---|---|---|
| LMArena Text | 1396 | 1056 |
| LMArena Creative Writing | 1372 | 1024 |
| LMArena Multi-Turn | 1409 | 963 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Gemma 7B?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.0 on the Noometry Index.

### Is Claude Haiku 4.5 or Gemma 7B better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 30.5 in the Noometry coding category.

### How many benchmarks do Claude Haiku 4.5 and Gemma 7B share?

14 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemma 7B has 27.