Model comparison
Claude Sonnet 4 vs GLM-4.6
Claude Sonnet 4 and GLM-4.6 score almost the same on the Noometry Index (40.8 vs 41.4), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Claude Sonnet 4 scores higher in 4 categories and GLM-4.6 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GLM-4.6 leads 43.4 to 33.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 73% for Claude Sonnet 4 and 47.4% for GLM-4.6.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- GLM-4.6 accepts more context: 205K tokens versus 200K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | GLM-4.6 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 40.8 | 41.4 |
| Released | 2025-05-22 | 2025-09-30 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $0.60 |
| Output $ / M tokens | $15 | $2.20 |
| Results tracked | 58 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), GLM-4.6: 40.1 (#148)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 55.4% |
| SciCode | 40% | 38.4% |
| LMArena Coding | 1414 | 1449 |
| ALE-Bench | 655.35 | 340.82 |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1340 |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), GLM-4.6: 32.3 (#66)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Too close to call
Claude Sonnet 4: 22.9 (#187), GLM-4.6: 23.7 (#172)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 73% | 47.4% |
| CritPt | 0.3% | 1.1% |
| LMArena Hard Prompts | 1372 | 1440 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), GLM-4.6: 39.1 (#111)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Math | 1375 | 1432 |
| FrontierMath (Feb 2025 set) | 4.1% | 3.8% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), GLM-4.6: 40.2 (#124)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 10.3% | 9.5% |
| LMArena Expert | 1372 | 1431 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), GLM-4.6: —
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual GLM-4.6 leads
Claude Sonnet 4: 46.7 (#156), GLM-4.6: 53.5 (#66)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1333 | 1426 |
| LMArena Chinese | 1350 | 1499 |
| LMArena French | 1363 | 1459 |
| LMArena German | 1331 | 1447 |
| LMArena Japanese | 1302 | 1393 |
| LMArena Korean | 1291 | 1400 |
| LMArena Russian | 1355 | 1419 |
| LMArena Spanish | 1357 | 1436 |
Instruction Following GLM-4.6 leads
Claude Sonnet 4: 71.7 (#145), GLM-4.6: 74.3 (#98)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1410 |
| IFEval | 84% | — |
Long Context GLM-4.6 leads
Claude Sonnet 4: 33.7 (#259), GLM-4.6: 43.4 (#94)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1398 | 1422 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference GLM-4.6 leads
Claude Sonnet 4: 57.1 (#132), GLM-4.6: 61.1 (#90)
| Benchmark | Claude Sonnet 4 | GLM-4.6 |
|---|---|---|
| LMArena Text | 1351 | 1440 |
| LMArena Creative Writing | 1345 | 1411 |
| EQ-Bench Creative Writing | 1483 | 1411 |
| LMArena Multi-Turn | 1376 | 1427 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GLM-4.6?
Claude Sonnet 4 and GLM-4.6 score almost the same on the Noometry Index (40.8 vs 41.4), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4 or GLM-4.6?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or GLM-4.6 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and GLM-4.6 share?
26 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GLM-4.6 has 29.