Model comparison
Claude Sonnet 4 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 40.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude Sonnet 4 scores higher in 3 categories and GLM-5V-Turbo in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GLM-5V-Turbo leads 40.1 to 25.6.
- GLM-5V-Turbo is cheaper at $1.20 / $4 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
Side by side
| Claude Sonnet 4 | GLM-5V-Turbo | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 40.6 | 43.1 |
| Released | 2025-05-22 | 2026-04-01 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $1.20 |
| Output $ / M tokens | $15 | $4 |
| Results tracked | 58 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Coding | 1414 | 1467 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1400 |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.3 (#29), GLM-5V-Turbo: —
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning GLM-5V-Turbo leads
Claude Sonnet 4: 23.0 (#169), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1443 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 41.5 (#71), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1375 | 1440 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.6 (#99), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1371 | 1451 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal GLM-5V-Turbo leads
Claude Sonnet 4: 25.6 (#116), GLM-5V-Turbo: 40.1 (#41)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | 1191 | 1264 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| LMArena Document | — | 1416 |
| MindCube | 44.8% | — |
Multilingual GLM-5V-Turbo leads
Claude Sonnet 4: 46.9 (#151), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1333 | 1420 |
| LMArena Chinese | 1351 | 1488 |
| LMArena French | 1364 | 1443 |
| LMArena German | 1331 | 1422 |
| LMArena Korean | 1293 | 1399 |
| LMArena Russian | 1355 | 1432 |
| LMArena Spanish | 1356 | 1446 |
| LMArena Japanese | 1301 | — |
Instruction Following GLM-5V-Turbo leads
Claude Sonnet 4: 71.8 (#141), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1375 | 1422 |
| IFEval | 84% | — |
Long Context GLM-5V-Turbo leads
Claude Sonnet 4: 33.6 (#254), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1398 | 1439 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference GLM-5V-Turbo leads
Claude Sonnet 4: 57.3 (#127), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | Claude Sonnet 4 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1351 | 1437 |
| LMArena Creative Writing | 1345 | 1414 |
| LMArena Multi-Turn | 1376 | 1432 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or GLM-5V-Turbo?
GLM-5V-Turbo is cheaper. It lists at $1.20 per million input tokens and $4 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or GLM-5V-Turbo better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Sonnet 4 and GLM-5V-Turbo share?
17 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GLM-5V-Turbo has 19.