Model comparison
Claude 3 Haiku vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 40.9 to 25.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-4.6V in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6V leads 56.8 to 29.8.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | GLM-4.6V | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.7 | 40.9 |
| Released | 2024-03-07 | 2025-12-08 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
Claude 3 Haiku: 26.1 (#320), GLM-4.6V: 40.2 (#128)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1199 | 1390 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning GLM-4.6V leads
Claude 3 Haiku: 15.7 (#303), GLM-4.6V: 26.5 (#117)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1368 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Not comparable
Claude 3 Haiku: 9.2 (#313), GLM-4.6V: —
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |
Knowledge GLM-4.6V leads
Claude 3 Haiku: 17.3 (#280), GLM-4.6V: 37.4 (#148)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1148 | 1372 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal GLM-4.6V leads
Claude 3 Haiku: 23.1 (#123), GLM-4.6V: 34.2 (#83)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Vision | 950 | 1164 |
| ScienceQA | 72% | — |
Multilingual GLM-4.6V leads
Claude 3 Haiku: 36.1 (#238), GLM-4.6V: 48.8 (#135)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1178 | 1359 |
| LMArena Chinese | 1155 | 1426 |
| LMArena Russian | 1204 | 1341 |
| LMArena French | 1194 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |
| LMArena Spanish | 1165 | — |
Instruction Following GLM-4.6V leads
Claude 3 Haiku: 61.5 (#242), GLM-4.6V: 71.6 (#145)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1174 | 1351 |
Long Context GLM-4.6V leads
Claude 3 Haiku: 36.1 (#232), GLM-4.6V: 41.3 (#138)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1191 | 1358 |
Writing & Preference GLM-4.6V leads
Claude 3 Haiku: 29.8 (#286), GLM-4.6V: 56.8 (#132)
| Benchmark | Claude 3 Haiku | GLM-4.6V |
|---|---|---|
| LMArena Text | 1195 | 1377 |
| LMArena Creative Writing | 1157 | 1347 |
| LMArena Multi-Turn | 1190 | 1359 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 40.9 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or GLM-4.6V better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.2 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and GLM-4.6V share?
12 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-4.6V has 12.