Model comparison
Claude 3.5 Sonnet vs GLM-5.2
GLM-5.2 is the stronger model overall, scoring 50.9 to 34.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 86.4% for GLM-5.2.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | GLM-5.2 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 34.4 | 50.9 |
| Released | 2024-06-20 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 60 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
Claude 3.5 Sonnet: 39.5 (#145), GLM-5.2: 50.9 (#37)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| WeirdML | 40% | 70.1% |
| LMArena Coding | 1343 | 1484 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1604 |
| SciCode | — | 50.5% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 1,047 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Too close to call
Claude 3.5 Sonnet: 32.1 (#61), GLM-5.2: 31.6 (#63)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| TheAgentCompany | 24% | — |
| τ²-bench Banking | — | 37.1% |
| Cybench | 17.5% | — |
| PostTrainBench | — | 31.7% |
| BALROG | 32.6% | — |
| GBAEval | — | 0% |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 8,314 |
Reasoning GLM-5.2 leads
Claude 3.5 Sonnet: 22.5 (#176), GLM-5.2: 42.1 (#46)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| SimpleBench | 41.4% | 58.8% |
| LMArena Hard Prompts | 1305 | 1480 |
| DTBench | 67.8% | 93.6% |
| Epoch Capabilities Index | 133.55 | 151.76 |
| ARC-AGI-2 | — | 22.8% |
| Kagi LLM Benchmark | — | 62.6% |
| NYT Connections (extended) | — | 74.3% |
| ARC-AGI-1 | — | 77% |
| CritPt | — | 20.9% |
| Chess Puzzles | — | 21% |
| EnigmaEval | 0.9% | — |
| EBR-Bench | — | 9.5% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 45.8% |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math GLM-5.2 leads
Claude 3.5 Sonnet: 18.0 (#282), GLM-5.2: 55.4 (#35)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 86.4% |
| LMArena Math | 1306 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 35% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-5.2 leads
Claude 3.5 Sonnet: 28.5 (#236), GLM-5.2: 57.1 (#36)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 55.3% | 91.9% |
| LMArena Expert | 1264 | 1484 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 34.2% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), GLM-5.2: —
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual GLM-5.2 leads
Claude 3.5 Sonnet: 43.4 (#180), GLM-5.2: 56.0 (#25)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1283 | 1459 |
| LMArena Chinese | 1271 | 1518 |
| LMArena French | 1304 | 1476 |
| LMArena German | 1297 | 1470 |
| LMArena Japanese | 1234 | 1451 |
| LMArena Korean | 1200 | 1445 |
| LMArena Russian | 1305 | 1467 |
| LMArena Spanish | 1289 | 1477 |
Instruction Following GLM-5.2 leads
Claude 3.5 Sonnet: 69.0 (#177), GLM-5.2: 77.1 (#32)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1465 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context GLM-5.2 leads
Claude 3.5 Sonnet: 39.9 (#162), GLM-5.2: 45.3 (#43)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1311 | 1479 |
Writing & Preference GLM-5.2 leads
Claude 3.5 Sonnet: 53.0 (#159), GLM-5.2: 70.7 (#20)
| Benchmark | Claude 3.5 Sonnet | GLM-5.2 |
|---|---|---|
| LMArena Text | 1298 | 1470 |
| LMArena Creative Writing | 1292 | 1465 |
| EQ-Bench Creative Writing | 1451 | 1757 |
| LMArena Multi-Turn | 1326 | 1468 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| EQ-Bench 4 | — | 1222 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GLM-5.2?
GLM-5.2 is the stronger model overall, scoring 50.9 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or GLM-5.2 better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and GLM-5.2 share?
24 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GLM-5.2 has 50.