Model comparison
Claude Sonnet 4.6 vs GLM-5.2
Claude Sonnet 4.6 and GLM-5.2 score almost the same on the Noometry Index (50.3 vs 51.1), so choose on price, context window or the category you care about most.
Last verified . 42 shared benchmarks.
Summary
- They share 42 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 3 categories and GLM-5.2 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 4.6 leads 39.1 to 32.4.
- The biggest single-benchmark swing is GBAEval: 48.8% for Claude Sonnet 4.6 and 0% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | GLM-5.2 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 50.3 | 51.1 |
| Released | 2026-02-17 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $3 | $1.40 |
| Output $ / M tokens | $15 | $4.40 |
| Results tracked | 57 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
Claude Sonnet 4.6: 46.3 (#67), GLM-5.2: 51.3 (#41)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| SWE-bench Verified | 75.2% | 78.7% |
| DeepSWE | 29.9% | 43.8% |
| FrontierCode | 24.3% | 24.5% |
| LMArena WebDev | 1522 | 1603 |
| SciCode | 46.8% | 50.5% |
| WeirdML | 66.1% | 70.1% |
| LMArena Coding | 1504 | 1485 |
| ALE-Bench | 1,327 | 1,047 |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#28), GLM-5.2: 32.4 (#63)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| APEX-Agents | 43% | 45.2% |
| GBAEval | 48.8% | 0% |
| Vending-Bench 2 | 7,204 | 8,314 |
| Terminal-Bench | 53.4% | — |
| OSWorld 2.0 | 9.3% | — |
| τ²-bench Banking | — | 37.1% |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| PostTrainBench | — | 31.7% |
| ExploitBench | 23.6% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), GLM-5.2: 42.3 (#52)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 22.8% |
| NYT Connections (extended) | 80.9% | 74.3% |
| ARC-AGI-1 | 86.5% | 77% |
| CritPt | 3.1% | 20.9% |
| Chess Puzzles | 13% | 21% |
| LMArena Hard Prompts | 1484 | 1480 |
| Mystery Game Puzzles | 16% | 19% |
| DTBench | 89.9% | 93.6% |
| LMCA | 46.5% | 45.8% |
| Epoch Capabilities Index | 152.24 | 151.78 |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 62.6% |
| Thematic Generalization | 76.3% | — |
| EBR-Bench | — | 9.5% |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 62 | — |
Math GLM-5.2 leads
Claude Sonnet 4.6: 52.9 (#49), GLM-5.2: 55.7 (#43)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 86.4% |
| ProofBench | 45% | 35% |
| LMArena Math | 1462 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge GLM-5.2 leads
Claude Sonnet 4.6: 51.7 (#65), GLM-5.2: 57.1 (#40)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 87.4% | 91.9% |
| SimpleQA Verified | 35.5% | 34.2% |
| LMArena Expert | 1500 | 1486 |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), GLM-5.2: —
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual GLM-5.2 leads
Claude Sonnet 4.6: 54.4 (#41), GLM-5.2: 55.8 (#26)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1440 | 1459 |
| LMArena Chinese | 1491 | 1519 |
| LMArena French | 1465 | 1479 |
| LMArena German | 1428 | 1468 |
| LMArena Japanese | 1420 | 1451 |
| LMArena Korean | 1411 | 1445 |
| LMArena Russian | 1440 | 1466 |
| LMArena Spanish | 1464 | 1477 |
Instruction Following Too close to call
Claude Sonnet 4.6: 77.4 (#25), GLM-5.2: 76.9 (#34)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1465 |
Long Context Too close to call
Claude Sonnet 4.6: 45.3 (#44), GLM-5.2: 45.3 (#43)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1479 | 1479 |
Writing & Preference Too close to call
Claude Sonnet 4.6: 70.2 (#22), GLM-5.2: 70.4 (#21)
| Benchmark | Claude Sonnet 4.6 | GLM-5.2 |
|---|---|---|
| LMArena Text | 1458 | 1470 |
| LMArena Creative Writing | 1435 | 1462 |
| EQ-Bench Creative Writing | 1810 | 1757 |
| EQ-Bench 4 | 1207 | 1222 |
| LMArena Multi-Turn | 1464 | 1469 |
Frequently asked questions
Is Claude Sonnet 4.6 better than GLM-5.2?
Claude Sonnet 4.6 and GLM-5.2 score almost the same on the Noometry Index (50.3 vs 51.1), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4.6 or GLM-5.2?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or GLM-5.2 better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and GLM-5.2 share?
42 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GLM-5.2 has 51.