# Claude 3 Haiku vs GLM-5.2

> GLM-5.2 is the stronger model overall, scoring 50.9 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 9.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 86.4% for GLM-5.2.
- GLM-5.2 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.7 | 50.9 |
| Rank | 333 | 38 |
| Context | — | 1M |
| Input $/M | — | $1.40 |
| Output $/M | — | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- GLM-5.2: 50.9 (#37)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| WeirdML | 9.8% | 70.1% |
| LMArena Coding | 1199 | 1484 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| LMArena WebDev | — | 1604 |
| SciCode | — | 50.5% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 1,047 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- GLM-5.2: 31.6 (#63)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- GLM-5.2: 42.1 (#46)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 62.6% |
| LMArena Hard Prompts | 1174 | 1480 |
| DTBench | 50.1% | 93.6% |
| LMCA | 8.8% | 45.8% |
| Epoch Capabilities Index | 118.3 | 151.76 |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| NYT Connections (extended) | — | 74.3% |
| ARC-AGI-1 | — | 77% |
| CritPt | — | 20.9% |
| Chess Puzzles | — | 21% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 19% |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- GLM-5.2: 55.4 (#35)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 86.4% |
| LMArena Math | 1188 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 35% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- GLM-5.2: 57.1 (#36)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 36.3% | 91.9% |
| LMArena Expert | 1148 | 1484 |
| SimpleQA Verified | — | 34.2% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- GLM-5.2: —

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- GLM-5.2: 56.0 (#25)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1178 | 1459 |
| LMArena Chinese | 1155 | 1518 |
| LMArena French | 1194 | 1476 |
| LMArena German | 1174 | 1470 |
| LMArena Japanese | 1102 | 1451 |
| LMArena Korean | 1108 | 1445 |
| LMArena Russian | 1204 | 1467 |
| LMArena Spanish | 1165 | 1477 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- GLM-5.2: 77.1 (#32)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1465 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- GLM-5.2: 45.3 (#43)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1191 | 1479 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- GLM-5.2: 70.7 (#20)

| Benchmark | Claude 3 Haiku | GLM-5.2 |
|---|---|---|
| LMArena Text | 1195 | 1470 |
| LMArena Creative Writing | 1157 | 1465 |
| EQ-Bench Creative Writing | 717 | 1757 |
| LMArena Multi-Turn | 1190 | 1468 |
| EQ-Bench 4 | — | 1222 |

## FAQ

### Is Claude 3 Haiku better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 50.9 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and GLM-5.2 share?

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-5.2 has 50.