Model comparison
Claude 3 Haiku vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-5V-Turbo in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5V-Turbo leads 62.5 to 29.7.
Side by side
| Claude 3 Haiku | GLM-5V-Turbo | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.9 | 43.8 |
| Released | 2024-03-07 | 2026-04-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $4 |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
Claude 3 Haiku: 26.4 (#325), GLM-5V-Turbo: 42.1 (#111)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1199 | 1466 |
| LMArena WebDev | — | 1401 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning GLM-5V-Turbo leads
Claude 3 Haiku: 16.3 (#307), GLM-5V-Turbo: 29.7 (#89)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1443 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math GLM-5V-Turbo leads
Claude 3 Haiku: 9.8 (#319), GLM-5V-Turbo: 39.4 (#106)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1188 | 1441 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge GLM-5V-Turbo leads
Claude 3 Haiku: 17.3 (#285), GLM-5V-Turbo: 40.6 (#117)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1148 | 1452 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal GLM-5V-Turbo leads
Claude 3 Haiku: 23.6 (#128), GLM-5V-Turbo: 40.9 (#42)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | 950 | 1264 |
| LMArena Document | — | 1416 |
| ScienceQA | 72% | — |
Multilingual GLM-5V-Turbo leads
Claude 3 Haiku: 36.0 (#243), GLM-5V-Turbo: 53.0 (#73)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1178 | 1420 |
| LMArena Chinese | 1155 | 1488 |
| LMArena French | 1195 | 1444 |
| LMArena German | 1174 | 1423 |
| LMArena Korean | 1109 | 1396 |
| LMArena Russian | 1204 | 1431 |
| LMArena Spanish | 1166 | 1450 |
| LMArena Japanese | 1102 | — |
Instruction Following GLM-5V-Turbo leads
Claude 3 Haiku: 61.3 (#247), GLM-5V-Turbo: 75.0 (#80)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1173 | 1423 |
Long Context GLM-5V-Turbo leads
Claude 3 Haiku: 36.1 (#237), GLM-5V-Turbo: 44.0 (#80)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1190 | 1438 |
Writing & Preference GLM-5V-Turbo leads
Claude 3 Haiku: 29.7 (#291), GLM-5V-Turbo: 62.5 (#73)
| Benchmark | Claude 3 Haiku | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1195 | 1437 |
| LMArena Creative Writing | 1157 | 1416 |
| LMArena Multi-Turn | 1190 | 1432 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or GLM-5V-Turbo better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 42.1 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and GLM-5V-Turbo share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-5V-Turbo has 19.