Model comparison
Claude Sonnet 4 vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 40.8 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude Sonnet 4 scores higher in 1 category and GLM-5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where GLM-5 leads 44.7 to 33.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 80% for GLM-5.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- GLM-5 accepts more context: 205K tokens versus 200K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | GLM-5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 40.8 | 46.1 |
| Released | 2025-05-22 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $1 |
| Output $ / M tokens | $15 | $3.20 |
| Results tracked | 58 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Claude Sonnet 4: 43.5 (#88), GLM-5: 49.0 (#52)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 72.8% |
| WeirdML | 46.1% | 48.2% |
| LMArena Coding | 1414 | 1461 |
| ALE-Bench | 655.35 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 40% | — |
| GSO | 4.9% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), GLM-5: 31.1 (#71)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| TheAgentCompany | 33.1% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Claude Sonnet 4: 22.9 (#187), GLM-5: 27.6 (#116)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| ARC-AGI-2 | 5.9% | 4.9% |
| SimpleBench | 45.5% | 53.2% |
| Kagi LLM Benchmark | 73% | 75% |
| ARC-AGI-1 | 40% | 44.7% |
| LMArena Hard Prompts | 1372 | 1452 |
| Epoch Capabilities Index | 141.69 | 145.83 |
| ForecastBench | 60.2 | 61 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 10% |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
Math GLM-5 leads
Claude Sonnet 4: 43.3 (#80), GLM-5: 46.4 (#71)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 80% |
| LMArena Math | 1375 | 1440 |
| FrontierMath (Feb 2025 set) | 4.1% | 16.4% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| MathArena Final-Answer Competitions | — | 65.7% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
Knowledge GLM-5 leads
Claude Sonnet 4: 41.8 (#108), GLM-5: 52.3 (#64)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| GPQA Diamond | 79.2% | 87.8% |
| Vectara Hallucination Rate | 10.3% | 10.1% |
| LMArena Expert | 1372 | 1454 |
| 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-5: —
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual GLM-5 leads
Claude Sonnet 4: 46.7 (#156), GLM-5: 53.7 (#58)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| LMArena Non-English | 1333 | 1430 |
| LMArena Chinese | 1350 | 1511 |
| LMArena French | 1363 | 1455 |
| LMArena German | 1331 | 1445 |
| LMArena Japanese | 1302 | 1416 |
| LMArena Korean | 1291 | 1423 |
| LMArena Russian | 1355 | 1436 |
| LMArena Spanish | 1357 | 1454 |
Instruction Following GLM-5 leads
Claude Sonnet 4: 71.7 (#145), GLM-5: 75.2 (#67)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1428 |
| IFEval | 84% | — |
Long Context GLM-5 leads
Claude Sonnet 4: 33.7 (#259), GLM-5: 44.7 (#60)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1398 | 1446 |
| Fiction.LiveBench | 46.9% | — |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Claude Sonnet 4: 57.1 (#132), GLM-5: 66.0 (#38)
| Benchmark | Claude Sonnet 4 | GLM-5 |
|---|---|---|
| LMArena Text | 1351 | 1446 |
| LMArena Creative Writing | 1345 | 1439 |
| EQ-Bench Creative Writing | 1483 | 1601 |
| LMArena Multi-Turn | 1376 | 1456 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 40.8 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or GLM-5?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 43.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and GLM-5 share?
32 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GLM-5 has 45.