Claude Sonnet 4.5 vs GLM 5.2
Updated October 21, 2026. 72 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Claude Sonnet 4.5 and GLM 5.2 are level for coding, 59.1 against 57.7 on the Vibe Coding Index, so price and context decide.
Pick GLM 5.2 when output tokens cost 2.1x less, or when a solved task costs $0.86 against $1.16. Pick Claude Sonnet 4.5 when what matters is LiveCodeBench (Vals AI) or LMArena Text: coding, where it leads.
- Shared results
- 72
- Claude Sonnet 4.5 only
- 20
- GLM 5.2 only
- 25
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
No call
Level: 59.1 against 57.7, inside 2 points.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 20.7.
Same board, both measured
Agentic work
AA Agentic Index
GLM 5.2
GLM 5.2 leads, 38.4 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
GLM 5.2
GLM 5.2 leads, 85.6% against 81.6%.
Same board, both measured
Math
AIME
No call
Only Claude Sonnet 4.5 has a AIME result, 88.2%.
Directional only
Knowledge
MMLU Pro
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 87.4% against 86.7%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1190.
Same board, both measured
Long documents
Listed context window
GLM 5.2
GLM 5.2 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5.2
Claude Sonnet 4.5 $0.011, GLM 5.2 $0.0035 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GLM 5.2
Claude Sonnet 4.5 $1.16, GLM 5.2 $0.86.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Sonnet 4.5 59.1 from 2 benchmarks, GLM 5.2 57.7 from 1 benchmark.
- Widest category
- Agentic work, 19.5 points apart on average over 5 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Sonnet 4.5 22.6% against GLM 5.2 64.0%, 41.3 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.5 $15.00 against GLM 5.2 $7.00 per million output tokens, 2.1x apart.
- Context window
- Claude Sonnet 4.5 takes 1M tokens, GLM 5.2 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Sonnet 4.5 | Bars | GLM 5.2 | Ties |
|---|---|---|---|---|
| Coding | 2 | 8 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 5 | ||
| Reasoning | 0 | 11 | ||
| Math | 0 | 6 | ||
| Knowledge | 3 | 7 | ||
| Web design | 1 | 7 | ||
| General | 1 | 19 | ||
| All shared boards | 7 | 65 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index28
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| SWE-bench Verified | 74.8% | Not measured | Only Claude Sonnet 4.5 measured |
| SWE-bench Multilingual | 67.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev | 1394 | 1604 | GLM 5.2 |
| AA Coding Index | 52.1 | 68.8 | GLM 5.2 |
| LiveCodeBench (Vals AI) | 73.0% | 69.5% | Claude Sonnet 4.5 |
| SWE-bench Verified (Vals AI) | 70.0% | 82.8% | GLM 5.2 |
| Vibe Code Bench (Vals AI) | 22.6% | 64.0% | GLM 5.2 |
| Code migration (Vals AI) | Not measured | 37.9% | Only GLM 5.2 measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only GLM 5.2 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 67.8% | Only GLM 5.2 measured |
| SkillsBench (Vals AI) | Not measured | 45.1% | Only GLM 5.2 measured |
| SciCode | Not measured | 51.2% | Only GLM 5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 50.8% | Only GLM 5.2 measured |
| Terminal-Bench | 46.5% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierCode | Not measured | 24.5% | Only GLM 5.2 measured |
| GSO-Bench | 14.7% | Not measured | Only Claude Sonnet 4.5 measured |
| WeirdML | 47.7% | 70.1% | GLM 5.2 |
| Cybench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| ALE-Bench | Not measured | 1047.0 | Only GLM 5.2 measured |
| LMArena Text: coding | 1488 | 1487 | Claude Sonnet 4.5 |
| LMArena Text: software and IT | 1473 | 1486 | GLM 5.2 |
| LMArena WebDev: React | 1386 | 1617 | GLM 5.2 |
| LMArena WebDev: HTML | 1399 | 1565 | GLM 5.2 |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.7 | 33.7 | GLM 5.2 |
| Epoch Capabilities Index | 146.7 | 151.9 | GLM 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| AA Agentic Index | 15.8 | 38.4 | GLM 5.2 |
| Design Arena: agents building web apps | 1060 | 1222 | GLM 5.2 |
| Design Arena: agents building full-stack apps | 1050 | 1241 | GLM 5.2 |
| Design Arena: agents building mobile apps | 1137 | 1160 | GLM 5.2 |
| Design Arena: agents building Android apps | Not measured | 1184 | Only GLM 5.2 measured |
| Design Arena: agents building Godot games | Not measured | 1142 | Only GLM 5.2 measured |
| Design Arena: agents building games | Not measured | 1206 | Only GLM 5.2 measured |
| Design Arena: HTML slides | Not measured | 1175 | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | Not measured | 1195 | Only GLM 5.2 measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | Not measured | 49.7% | Only GLM 5.2 measured |
| Legal Research Bench (Vals AI) | Not measured | 31.3% | Only GLM 5.2 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 61.5% | Only GLM 5.2 measured |
| τ²-Bench Telecom | Not measured | 99.1% | Only GLM 5.2 measured |
| APEX-Agents | Not measured | 45.2% | Only GLM 5.2 measured |
| METR time horizons | 67.4% | Not measured | Only Claude Sonnet 4.5 measured |
| Remote Labor Index | 2.1% | Not measured | Only Claude Sonnet 4.5 measured |
| GDPval | 42.5% | Not measured | Only Claude Sonnet 4.5 measured |
| DeepResearch Bench | 52.6% | Not measured | Only Claude Sonnet 4.5 measured |
| PostTrainBench | Not measured | 31.7% | Only GLM 5.2 measured |
| OSWorld | 62.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Vending-Bench 2 | $3,839 | $8,314 | GLM 5.2 |
| Neither model has a result on the other 17 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| GPQA Diamond | 81.6% | 85.6% | GLM 5.2 |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only Claude Sonnet 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.5% | Only GLM 5.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 41.1% | Only GLM 5.2 measured |
| GPQA Diamond (Epoch AI run) | 82.3% | 91.9% | GLM 5.2 |
| ARC-AGI | 63.7% | 77.0% | GLM 5.2 |
| ARC-AGI-2 | 13.6% | 22.8% | GLM 5.2 |
| SimpleBench | 54.3% | 58.8% | GLM 5.2 |
| Chess puzzles | 10.0% | 22.0% | GLM 5.2 |
| Mystery game puzzles | 17.0% | 19.0% | GLM 5.2 |
| EBR-bench | 2.4% | 9.5% | GLM 5.2 |
| VPCT | 39.8% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: hard prompts | 1462 | 1481 | GLM 5.2 |
| LMArena Text: expert | 1483 | 1487 | GLM 5.2 |
| LMArena Text: hard prompts in English | 1471 | 1481 | GLM 5.2 |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| AIME | 88.2% | Not measured | Only Claude Sonnet 4.5 measured |
| MGSM (Vals AI) | 94.3% | Not measured | Only Claude Sonnet 4.5 measured |
| OTIS Mock AIME | 77.8% | 86.4% | GLM 5.2 |
| FrontierMath, tiers 1 to 3 | 23.9% | 59.2% | GLM 5.2 |
| FrontierMath, tier 4 | 2.4% | 29.3% | GLM 5.2 |
| ProofBench | 19.0% | 35.0% | GLM 5.2 |
| MATH level 5 | 97.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: math | 1449 | 1483 | GLM 5.2 |
| LMArena Text: mathematical work | 1462 | 1489 | GLM 5.2 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| MMLU Pro | 87.4% | 86.7% | Claude Sonnet 4.5 |
| LegalBench (Vals AI) | 84.1% | 84.1% | Claude Sonnet 4.5 |
| CaseLaw (Vals AI) | 62.2% | Not measured | Only Claude Sonnet 4.5 measured |
| CorpFin (Vals AI) | 62.0% | 66.1% | GLM 5.2 |
| TaxEval (Vals AI) | 73.3% | 73.3% | GLM 5.2 |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MedQA (Vals AI) | 94.7% | Not measured | Only Claude Sonnet 4.5 measured |
| MedCode (Vals AI) | 44.1% | 40.8% | Claude Sonnet 4.5 |
| SimpleQA Verified | 30.7% | 34.2% | GLM 5.2 |
| LMArena Text: science | 1448 | 1489 | GLM 5.2 |
| LMArena Text: medicine and healthcare | 1444 | 1475 | GLM 5.2 |
| LMArena Text: legal and government | 1451 | 1486 | GLM 5.2 |
| LMArena Text: business and finance | 1440 | 1451 | GLM 5.2 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| Design Arena: websites | 1190 | 1285 | GLM 5.2 |
| Design Arena: UI components | 1173 | 1296 | GLM 5.2 |
| Design Arena: game dev | 1166 | 1268 | GLM 5.2 |
| Design Arena: data viz | 1167 | 1285 | GLM 5.2 |
| Design Arena: 3D | 1158 | 1288 | GLM 5.2 |
| Design Arena: all code categories | 1183 | 1288 | GLM 5.2 |
| Design Arena: SVG | 1114 | 1214 | GLM 5.2 |
| Design Arena: ASCII art | 1204 | 1190 | Claude Sonnet 4.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index119
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 36.1% | Not measured | Only Claude Sonnet 4.5 measured |
| MedScribe (Vals AI) | 84.5% | 83.5% | Claude Sonnet 4.5 |
| IFBench | Not measured | 73.3% | Only GLM 5.2 measured |
| Long context reasoning (AA-LCR) | Not measured | 78.3% | Only GLM 5.2 measured |
| DTBench | 83.2% | 93.6% | GLM 5.2 |
| LMCA | 38.8% | 45.8% | GLM 5.2 |
| Surface Evolver Bench | Not measured | 55.6% | Only GLM 5.2 measured |
| LMArena Text | 1438 | 1470 | GLM 5.2 |
| LMArena Text: instruction following | 1459 | 1466 | GLM 5.2 |
| LMArena Text: creative writing | 1442 | 1463 | GLM 5.2 |
| LMArena Text: English | 1450 | 1475 | GLM 5.2 |
| LMArena Text: non-English | 1425 | 1459 | GLM 5.2 |
| LMArena Text: Chinese | 1460 | 1522 | GLM 5.2 |
| LMArena Text: German | 1427 | 1470 | GLM 5.2 |
| LMArena Text: Japanese | 1390 | 1450 | GLM 5.2 |
| LMArena Text: Korean | 1402 | 1440 | GLM 5.2 |
| LMArena Text: French | 1459 | 1479 | GLM 5.2 |
| LMArena Text: Spanish | 1458 | 1478 | GLM 5.2 |
| LMArena Text: Russian | 1437 | 1468 | GLM 5.2 |
| LMArena Text: Polish | 1423 | 1456 | GLM 5.2 |
| LMArena Text: multi-turn | 1465 | 1469 | GLM 5.2 |
| LMArena Text: longer queries | 1475 | 1480 | GLM 5.2 |
| LMArena Text: writing and language | 1442 | 1463 | GLM 5.2 |
| LMArena Text: entertainment and media | 1428 | 1450 | GLM 5.2 |
| LMArena Document | 1450 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.5 | GLM 5.2 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GLM 5.2 costs less
Repository review
50K input + 3K output tokens
GLM 5.2 costs less
Agent loop
200K input + 10K output tokens
GLM 5.2 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Sonnet 4.5 | Z.ai GLM 5.2 |
|---|---|---|
| Maker | Anthropic | Z.ai |
| Weights | No public weights listed | Open weights |
| Released | September 29, 2025 | June 16, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $3.00 | $0.0341 |
| Output $/Mtok | $15.00 | $7.00 |
| Coding index | 59.1 | 57.7 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $1.16 | $0.86 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.5 better than GLM 5.2 for coding?
Claude Sonnet 4.5 and GLM 5.2 are level for coding, 59.1 against 57.7 on the Vibe Coding Index, so price and context decide. Pick GLM 5.2 when output tokens cost 2.1x less, or when a solved task costs $0.86 against $1.16. Pick Claude Sonnet 4.5 when what matters is LiveCodeBench (Vals AI) or LMArena Text: coding, where it leads.
Which is cheaper, Claude Sonnet 4.5 or GLM 5.2?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GLM 5.2 costs $0.0341 and $7.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and GLM 5.2 $0.86.
Which has the bigger context window, Claude Sonnet 4.5 or GLM 5.2?
GLM 5.2, with 1.05M tokens against 1M.
How many benchmarks is the Claude Sonnet 4.5 vs GLM 5.2 comparison based on?
72 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.5's coding index rests on 2 independent benchmarks and GLM 5.2's on 1. Where only one model has a result, the page says so instead of naming a winner.