# Claude 3 Haiku vs GLM-4.7-Flash

> GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-glm-4-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-4.7-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 9.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 58.3% for GLM-4.7-Flash.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.7 | 38.4 |
| Rank | 333 | 175 |
| Context | — | 200K |
| Input $/M | — | $0.06 |
| Output $/M | — | $0.40 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- GLM-4.7-Flash: 40.0 (#133)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Coding | 1199 | 1383 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- GLM-4.7-Flash: 20.2 (#224)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1356 |
| Kagi LLM Benchmark | 34.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- GLM-4.7-Flash: 34.4 (#159)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 58.3% |
| LMArena Math | 1188 | 1354 |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- GLM-4.7-Flash: 35.4 (#177)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| GPQA Diamond | 36.3% | 60.5% |
| LMArena Expert | 1148 | 1357 |
| Confabulations | 34.2% | — |
| Vectara Hallucination Rate | — | 9.3% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- GLM-4.7-Flash: —

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- GLM-4.7-Flash: 46.8 (#152)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | 1178 | 1331 |
| LMArena Chinese | 1155 | 1403 |
| LMArena French | 1194 | 1332 |
| LMArena German | 1174 | 1336 |
| LMArena Korean | 1108 | 1284 |
| LMArena Russian | 1204 | 1333 |
| LMArena Spanish | 1165 | 1351 |
| LMArena Japanese | 1102 | — |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- GLM-4.7-Flash: 70.3 (#162)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | 1174 | 1327 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- GLM-4.7-Flash: 40.9 (#143)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | 1191 | 1345 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- GLM-4.7-Flash: 47.7 (#206)

| Benchmark | Claude 3 Haiku | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | 1195 | 1351 |
| LMArena Creative Writing | 1157 | 1297 |
| EQ-Bench Creative Writing | 717 | 1125 |
| LMArena Multi-Turn | 1190 | 1342 |

## FAQ

### Is Claude 3 Haiku better than GLM-4.7-Flash?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or GLM-4.7-Flash better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and GLM-4.7-Flash share?

19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-4.7-Flash has 21.