Model comparison
Claude 3 Sonnet vs GLM-4.5
GLM-4.5 is the stronger model overall, scoring 42.0 to 29.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-4.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5 leads 39.0 to 10.7.
- The biggest single-benchmark swing is WeirdML: 10.2% for Claude 3 Sonnet and 40.6% for GLM-4.5.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | GLM-4.5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 29.0 | 42.0 |
| Released | 2024-02-29 | 2025-07-27 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 30 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
Claude 3 Sonnet: 29.6 (#302), GLM-4.5: 41.4 (#125)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| WeirdML | 10.2% | 40.6% |
| LMArena Coding | 1223 | 1434 |
| SWE-bench Verified (bash only) | — | 54.2% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 344.82 |
| AlgoTune | — | 1.52 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning GLM-4.5 leads
Claude 3 Sonnet: 20.5 (#237), GLM-4.5: 28.6 (#100)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1429 |
| Kagi LLM Benchmark | — | 57.9% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math GLM-4.5 leads
Claude 3 Sonnet: 10.7 (#310), GLM-4.5: 39.0 (#116)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Math | 1213 | 1427 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge GLM-4.5 leads
Claude 3 Sonnet: 21.1 (#276), GLM-4.5: 35.9 (#179)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Expert | 1173 | 1433 |
| GPQA Diamond | 40.6% | — |
| Humanity's Last Exam | — | 8.3% |
| Confabulations | — | 11.3% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), GLM-4.5: —
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual GLM-4.5 leads
Claude 3 Sonnet: 37.8 (#234), GLM-4.5: 52.8 (#77)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1205 | 1417 |
| LMArena Chinese | 1189 | 1465 |
| LMArena French | 1229 | 1418 |
| LMArena German | 1204 | 1407 |
| LMArena Japanese | 1131 | 1415 |
| LMArena Korean | 1128 | 1380 |
| LMArena Russian | 1227 | 1414 |
| LMArena Spanish | 1204 | 1454 |
Instruction Following GLM-4.5 leads
Claude 3 Sonnet: 62.8 (#235), GLM-4.5: 74.1 (#104)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1404 |
Long Context GLM-4.5 leads
Claude 3 Sonnet: 36.7 (#228), GLM-4.5: 38.2 (#201)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Longer Query | 1211 | 1412 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference GLM-4.5 leads
Claude 3 Sonnet: 42.1 (#238), GLM-4.5: 57.5 (#127)
| Benchmark | Claude 3 Sonnet | GLM-4.5 |
|---|---|---|
| LMArena Text | 1218 | 1430 |
| LMArena Creative Writing | 1186 | 1395 |
| LMArena Multi-Turn | 1227 | 1415 |
| Short-Story Creative Writing | — | 73.4% |
| EQ-Bench Creative Writing | — | 1343 |
Frequently asked questions
Is Claude 3 Sonnet better than GLM-4.5?
GLM-4.5 is the stronger model overall, scoring 42.0 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or GLM-4.5 better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.4 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and GLM-4.5 share?
18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-4.5 has 27.