Model comparison
Claude 3 Haiku vs GLM-4.5V
GLM-4.5V is the stronger model overall, scoring 39.2 to 25.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-4.5V in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5V leads 34.7 to 9.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 59.8% for GLM-4.5V.
- GLM-4.5V has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | GLM-4.5V | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.7 | 39.2 |
| Released | 2024-03-07 | 2025-08-11 |
| Weights | Proprietary | Open |
| Context window | — | 64K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $1.80 |
| Results tracked | 37 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5V leads
Claude 3 Haiku: 26.1 (#320), GLM-4.5V: 38.9 (#152)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Coding | 1199 | 1347 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning GLM-4.5V leads
Claude 3 Haiku: 15.7 (#303), GLM-4.5V: 26.5 (#118)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 59.8% |
| LMArena Hard Prompts | 1174 | 1335 |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math GLM-4.5V leads
Claude 3 Haiku: 9.2 (#313), GLM-4.5V: 34.7 (#157)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Math | 1188 | 1353 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge GLM-4.5V leads
Claude 3 Haiku: 17.3 (#280), GLM-4.5V: 36.8 (#155)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Expert | 1148 | 1353 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal GLM-4.5V leads
Claude 3 Haiku: 23.1 (#123), GLM-4.5V: 33.6 (#86)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Vision | 950 | 1154 |
| ScienceQA | 72% | — |
Multilingual GLM-4.5V leads
Claude 3 Haiku: 36.1 (#238), GLM-4.5V: 44.9 (#172)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Non-English | 1178 | 1304 |
| LMArena Chinese | 1155 | 1338 |
| LMArena Russian | 1204 | 1299 |
| LMArena Spanish | 1165 | 1335 |
| LMArena French | 1194 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |
Instruction Following GLM-4.5V leads
Claude 3 Haiku: 61.5 (#242), GLM-4.5V: 69.4 (#170)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Instruction Following | 1174 | 1311 |
Long Context GLM-4.5V leads
Claude 3 Haiku: 36.1 (#232), GLM-4.5V: 39.6 (#166)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Longer Query | 1191 | 1305 |
Writing & Preference GLM-4.5V leads
Claude 3 Haiku: 29.8 (#286), GLM-4.5V: 52.7 (#162)
| Benchmark | Claude 3 Haiku | GLM-4.5V |
|---|---|---|
| LMArena Text | 1195 | 1333 |
| LMArena Creative Writing | 1157 | 1295 |
| LMArena Multi-Turn | 1190 | 1333 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than GLM-4.5V?
GLM-4.5V is the stronger model overall, scoring 39.2 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or GLM-4.5V better for coding?
GLM-4.5V scores higher on coding benchmarks: 38.9 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and GLM-4.5V share?
15 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-4.5V has 15.