# Claude 3 Haiku vs GLM-4.5

> GLM-4.5 is the stronger model overall, scoring 42.0 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-glm-4-5
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-4.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 9.8.
- The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 40.6% for GLM-4.5.
- GLM-4.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.9 | 42.0 |
| Rank | 340 | 122 |
| Context | — | 131K |
| Input $/M | — | $0.60 |
| Output $/M | — | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- GLM-4.5: 41.4 (#125)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| WeirdML | 9.8% | 40.6% |
| LMArena Coding | 1199 | 1434 |
| SWE-bench Verified (bash only) | — | 54.2% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 344.82 |
| AlgoTune | — | 1.52 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- GLM-4.5: 28.6 (#100)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 57.9% |
| LMArena Hard Prompts | 1174 | 1429 |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- GLM-4.5: 39.0 (#116)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Math | 1188 | 1427 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- GLM-4.5: 35.9 (#179)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| Confabulations | 34.2% | 11.3% |
| LMArena Expert | 1148 | 1433 |
| GPQA Diamond | 36.3% | — |
| Humanity's Last Exam | — | 8.3% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- GLM-4.5: —

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- GLM-4.5: 52.8 (#77)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1178 | 1417 |
| LMArena Chinese | 1155 | 1465 |
| LMArena French | 1195 | 1418 |
| LMArena German | 1174 | 1407 |
| LMArena Japanese | 1102 | 1415 |
| LMArena Korean | 1109 | 1380 |
| LMArena Russian | 1204 | 1414 |
| LMArena Spanish | 1166 | 1454 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- GLM-4.5: 74.1 (#104)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1404 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- GLM-4.5: 38.2 (#201)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Longer Query | 1190 | 1412 |
| Fiction.LiveBench | — | 58.3% |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- GLM-4.5: 57.5 (#127)

| Benchmark | Claude 3 Haiku | GLM-4.5 |
|---|---|---|
| LMArena Text | 1195 | 1430 |
| LMArena Creative Writing | 1157 | 1395 |
| EQ-Bench Creative Writing | 717 | 1343 |
| LMArena Multi-Turn | 1190 | 1415 |
| Short-Story Creative Writing | — | 73.4% |

## FAQ

### Is Claude 3 Haiku better than GLM-4.5?

GLM-4.5 is the stronger model overall, scoring 42.0 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or GLM-4.5 better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and GLM-4.5 share?

21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-4.5 has 27.