Model comparison
Claude 3 Sonnet vs GLM-4.5-Air
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-4.5-Air in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 36.2 to 10.7.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | GLM-4.5-Air | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 29.0 | 38.9 |
| Released | 2024-02-29 | 2025-07-20 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 98K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $1.10 |
| Results tracked | 30 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
Claude 3 Sonnet: 29.6 (#302), GLM-4.5-Air: 33.3 (#259)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1223 | 1397 |
| GSO | — | 2.9% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning GLM-4.5-Air leads
Claude 3 Sonnet: 20.5 (#237), GLM-4.5-Air: 24.1 (#166)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| ForecastBench | — | 59.2 |
| WinoGrande | 75.1% | — |
Math GLM-4.5-Air leads
Claude 3 Sonnet: 10.7 (#310), GLM-4.5-Air: 36.2 (#170)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1213 | 1396 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| Omni-MATH | — | 39.1% |
| MATH Level 5 | 18.2% | — |
Knowledge GLM-4.5-Air leads
Claude 3 Sonnet: 21.1 (#276), GLM-4.5-Air: 35.0 (#191)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Expert | 1173 | 1370 |
| GPQA Diamond | 40.6% | — |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), GLM-4.5-Air: —
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual GLM-4.5-Air leads
Claude 3 Sonnet: 37.8 (#234), GLM-4.5-Air: 49.1 (#135)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1205 | 1366 |
| LMArena Chinese | 1189 | 1426 |
| LMArena French | 1229 | 1399 |
| LMArena German | 1204 | 1377 |
| LMArena Japanese | 1131 | 1348 |
| LMArena Korean | 1128 | 1308 |
| LMArena Russian | 1227 | 1373 |
| LMArena Spanish | 1204 | 1386 |
Instruction Following GLM-4.5-Air leads
Claude 3 Sonnet: 62.8 (#235), GLM-4.5-Air: 69.6 (#171)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1199 | 1354 |
| IFEval | — | 81.2% |
Long Context GLM-4.5-Air leads
Claude 3 Sonnet: 36.7 (#228), GLM-4.5-Air: 41.6 (#135)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1211 | 1366 |
Writing & Preference GLM-4.5-Air leads
Claude 3 Sonnet: 42.1 (#238), GLM-4.5-Air: 55.9 (#139)
| Benchmark | Claude 3 Sonnet | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1218 | 1384 |
| LMArena Creative Writing | 1186 | 1343 |
| LMArena Multi-Turn | 1227 | 1371 |
| WildBench | — | 78.9% |
Frequently asked questions
Is Claude 3 Sonnet better than GLM-4.5-Air?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or GLM-4.5-Air better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and GLM-4.5-Air share?
17 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-4.5-Air has 27.