Model comparison
Claude Sonnet 5 vs GLM-5.2
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 51.1 on the Noometry Index. GLM-5.2 costs 1.9× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 43 shared benchmarks.
Summary
- They share 43 benchmarks with published results for both. Claude Sonnet 5 scores higher in 4 categories and GLM-5.2 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 55.7.
- The biggest single-benchmark swing is GBAEval: 65.3% for Claude Sonnet 5 and 0% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | GLM-5.2 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 54.6 | 51.1 |
| Released | 2026-06-29 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $1.40 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), GLM-5.2: 51.3 (#41)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| DeepSWE | 53.8% | 43.8% |
| FrontierCode | 42.7% | 24.5% |
| LMArena WebDev | 1541 | 1603 |
| SciCode | 54.3% | 50.5% |
| WeirdML | 68.8% | 70.1% |
| LMArena Coding | 1483 | 1485 |
| ALE-Bench | 1,463 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), GLM-5.2: 32.4 (#63)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| APEX-Agents | 54.5% | 45.2% |
| GBAEval | 65.3% | 0% |
| Vending-Bench 2 | 6,378 | 8,314 |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| LMArena Search | 1194 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), GLM-5.2: 42.3 (#52)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| SimpleBench | 60.6% | 58.8% |
| NYT Connections (extended) | 75.1% | 74.3% |
| CritPt | 16.9% | 20.9% |
| Chess Puzzles | 35% | 21% |
| LMArena Hard Prompts | 1461 | 1480 |
| Mystery Game Puzzles | 35% | 19% |
| DTBench | 92.5% | 93.6% |
| LMCA | 50% | 45.8% |
| Surface Evolver Bench | 60% | 55.6% |
| Epoch Capabilities Index | 156.21 | 151.78 |
| ARC-AGI-2 | — | 22.8% |
| Kagi LLM Benchmark | — | 62.6% |
| ARC-AGI-1 | — | 77% |
| EBR-Bench | — | 9.5% |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), GLM-5.2: 55.7 (#43)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 59.2% |
| FrontierMath Tier 4 | 29.3% | 29.3% |
| OTIS Mock AIME 2024-2025 | 94.7% | 86.4% |
| ProofBench | 77% | 35% |
| LMArena Math | 1467 | 1482 |
| MathArena Final-Answer Competitions | — | 67.6% |
Knowledge GLM-5.2 leads
Claude Sonnet 5: 55.6 (#47), GLM-5.2: 57.1 (#40)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 90.5% | 91.9% |
| SimpleQA Verified | 33.7% | 34.2% |
| LMArena Expert | 1490 | 1486 |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), GLM-5.2: —
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual GLM-5.2 leads
Claude Sonnet 5: 53.8 (#55), GLM-5.2: 55.8 (#26)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1431 | 1459 |
| LMArena Chinese | 1477 | 1519 |
| LMArena French | 1460 | 1479 |
| LMArena German | 1440 | 1468 |
| LMArena Japanese | 1422 | 1451 |
| LMArena Korean | 1411 | 1445 |
| LMArena Russian | 1451 | 1466 |
| LMArena Spanish | 1437 | 1477 |
Instruction Following Too close to call
Claude Sonnet 5: 76.3 (#41), GLM-5.2: 76.9 (#34)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1465 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), GLM-5.2: 45.3 (#43)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1463 | 1479 |
Writing & Preference GLM-5.2 leads
Claude Sonnet 5: 69.2 (#25), GLM-5.2: 70.4 (#21)
| Benchmark | Claude Sonnet 5 | GLM-5.2 |
|---|---|---|
| LMArena Text | 1442 | 1470 |
| LMArena Creative Writing | 1416 | 1462 |
| EQ-Bench Creative Writing | 1794 | 1757 |
| EQ-Bench 4 | 1236 | 1222 |
| LMArena Multi-Turn | 1454 | 1469 |
Frequently asked questions
Is Claude Sonnet 5 better than GLM-5.2?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 51.1 on the Noometry Index. GLM-5.2 costs 1.9× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 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 5 lists at $2 and $10.
Is Claude Sonnet 5 or GLM-5.2 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 5 and GLM-5.2 share?
43 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GLM-5.2 has 51.