Claude Opus 4.5 vs GLM 5
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
Pick Claude Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 59.7 for GLM 5.
Pick GLM 5 when output tokens cost 7.8x less, or when a solved task costs $0.63 against $1.37.
- Shared results
- 72
- Claude Opus 4.5 only
- 33
- GLM 5 only
- 3
- 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
Claude Opus 4.5
Claude Opus 4.5 scores 66.8 against 59.7.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Claude Opus 4.5
Claude Opus 4.5 leads, 29.1 against 27.9.
Same board, both measured
Reasoning
GPQA Diamond
Claude Opus 4.5
Claude Opus 4.5 leads, 85.9% against 83.3%.
Same board, both measured
Math
AIME
Claude Opus 4.5
Claude Opus 4.5 leads, 95.4% against 91.7%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.5
Claude Opus 4.5 leads, 87.3% against 86.0%.
Same board, both measured
Web design
Design Arena: websites
No call
Tied at 1247.
Same board, both measured
Long documents
Listed context window
GLM 5
GLM 5 takes 205K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5
Claude Opus 4.5 $0.018, GLM 5 $0.0026 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GLM 5
Claude Opus 4.5 $1.37, GLM 5 $0.63.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.5 66.8 from 2 benchmarks, GLM 5 59.7 from 2 benchmarks.
- Widest category
- Reasoning, 10.0 points apart on average over 10 shared benchmarks.
- Widest single gap
- ARC-AGI: Claude Opus 4.5 80.0% against GLM 5 44.7%, 35.3 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.5 $25.00 against GLM 5 $3.20 per million output tokens, 7.8x apart.
- Context window
- Claude Opus 4.5 takes 200K tokens, GLM 5 205K.
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 Opus 4.5 | Bars | GLM 5 | Ties |
|---|---|---|---|---|
| Coding | 12 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 4 | 1 | ||
| Reasoning | 9 | 1 | ||
| Math | 4 | 0 | ||
| Knowledge | 8 | 2 | ||
| Web design | 4 | 3 | 1 tie | |
| General | 18 | 2 | ||
| All shared boards | 61 | 10 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index121
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 79.2% | 72.8% | Claude Opus 4.5 |
| SWE-bench (full test set) | 52.6% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Multilingual | 70.7% | 69.7% | Claude Opus 4.5 |
| LMArena WebDev | 1494 | 1435 | Claude Opus 4.5 |
| LiveCodeBench (Vals AI) | 83.7% | 81.9% | Claude Opus 4.5 |
| SWE-bench Verified (Vals AI) | 76.4% | 71.4% | Claude Opus 4.5 |
| Vibe Code Bench (Vals AI) | 20.6% | 23.4% | GLM 5 |
| LiveCodeBench (Artificial Analysis run) | 87.1% | Not measured | Only Claude Opus 4.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 43.2% | Claude Opus 4.5 |
| Terminal-Bench | 63.1% | 52.4% | Claude Opus 4.5 |
| GSO-Bench | 26.5% | Not measured | Only Claude Opus 4.5 measured |
| WeirdML | 63.7% | 48.2% | Claude Opus 4.5 |
| Cybench | 82.0% | Not measured | Only Claude Opus 4.5 measured |
| ALE-Bench | Not measured | 765.6 | Only GLM 5 measured |
| LMArena Text: coding | 1503 | 1461 | Claude Opus 4.5 |
| LMArena Text: software and IT | 1483 | 1460 | Claude Opus 4.5 |
| LMArena WebDev: React | 1478 | 1424 | Claude Opus 4.5 |
| LMArena WebDev: HTML | 1510 | 1450 | Claude Opus 4.5 |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.1 | 27.9 | Claude Opus 4.5 |
| Epoch Capabilities Index | 150.1 | 145.8 | Claude Opus 4.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1159 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building full-stack apps | 1156 | 1123 | Claude Opus 4.5 |
| Design Arena: agents building mobile apps | 1189 | 1136 | Claude Opus 4.5 |
| Design Arena: agents building Android apps | 1181 | 1152 | Claude Opus 4.5 |
| Design Arena: agents building Godot games | Not measured | 1144 | Only GLM 5 measured |
| Design Arena: HTML slides | Not measured | 1148 | Only GLM 5 measured |
| τ²-Bench Telecom | 89.5% | 98.2% | GLM 5 |
| METR time horizons | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| Remote Labor Index | 3.8% | Not measured | Only Claude Opus 4.5 measured |
| GDPval | 45.5% | Not measured | Only Claude Opus 4.5 measured |
| BALROG | 43.5% | Not measured | Only Claude Opus 4.5 measured |
| DeepResearch Bench | 54.8% | Not measured | Only Claude Opus 4.5 measured |
| OSWorld | 66.3% | Not measured | Only Claude Opus 4.5 measured |
| Vending-Bench 2 | $4,967 | $4,432 | Claude Opus 4.5 |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.9% | 83.3% | Claude Opus 4.5 |
| MMMU Pro (Vals AI) | 83.0% | Not measured | Only Claude Opus 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | 86.6% | 82.0% | Claude Opus 4.5 |
| Humanity's Last Exam (Artificial Analysis run) | 30.1% | 29.3% | Claude Opus 4.5 |
| GPQA Diamond (Epoch AI run) | 86.0% | 87.8% | GLM 5 |
| ARC-AGI | 80.0% | 44.7% | Claude Opus 4.5 |
| ARC-AGI-2 | 37.6% | 4.9% | Claude Opus 4.5 |
| SimpleBench | 62.0% | 53.2% | Claude Opus 4.5 |
| Chess puzzles | 14.0% | Not measured | Only Claude Opus 4.5 measured |
| Mystery game puzzles | 22.0% | Not measured | Only Claude Opus 4.5 measured |
| EBR-bench | 14.3% | Not measured | Only Claude Opus 4.5 measured |
| VPCT | 40.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: hard prompts | 1476 | 1452 | Claude Opus 4.5 |
| LMArena Text: expert | 1487 | 1454 | Claude Opus 4.5 |
| LMArena Text: hard prompts in English | 1482 | 1460 | Claude Opus 4.5 |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| AIME | 95.4% | 91.7% | Claude Opus 4.5 |
| MGSM (Vals AI) | 95.2% | Not measured | Only Claude Opus 4.5 measured |
| AA Math Index | 91.3 | Not measured | Only Claude Opus 4.5 measured |
| AIME 2025 (Artificial Analysis run) | 91.3% | Not measured | Only Claude Opus 4.5 measured |
| OTIS Mock AIME | 86.1% | 80.0% | Claude Opus 4.5 |
| FrontierMath, tiers 1 to 3 | 34.4% | Not measured | Only Claude Opus 4.5 measured |
| FrontierMath, tier 4 | 4.9% | Not measured | Only Claude Opus 4.5 measured |
| ProofBench | 36.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: math | 1463 | 1440 | Claude Opus 4.5 |
| LMArena Text: mathematical work | 1468 | 1451 | Claude Opus 4.5 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 86.0% | Claude Opus 4.5 |
| LegalBench (Vals AI) | 84.6% | 84.1% | Claude Opus 4.5 |
| CaseLaw (Vals AI) | 62.6% | 52.5% | Claude Opus 4.5 |
| CorpFin (Vals AI) | 65.1% | 62.9% | Claude Opus 4.5 |
| TaxEval (Vals AI) | 74.9% | 70.0% | Claude Opus 4.5 |
| MortgageTax (Vals AI) | 68.7% | Not measured | Only Claude Opus 4.5 measured |
| MedQA (Vals AI) | 95.9% | 94.3% | Claude Opus 4.5 |
| MedCode (Vals AI) | 49.2% | Not measured | Only Claude Opus 4.5 measured |
| MMLU Pro (Artificial Analysis run) | 89.5% | Not measured | Only Claude Opus 4.5 measured |
| SimpleQA Verified | 45.7% | Not measured | Only Claude Opus 4.5 measured |
| GeoBench | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: science | 1454 | 1460 | GLM 5 |
| LMArena Text: medicine and healthcare | 1444 | 1455 | GLM 5 |
| LMArena Text: legal and government | 1459 | 1453 | Claude Opus 4.5 |
| LMArena Text: business and finance | 1448 | 1430 | Claude Opus 4.5 |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index43
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1247 | 1247 | Tie |
| Design Arena: UI components | 1238 | 1230 | Claude Opus 4.5 |
| Design Arena: game dev | 1229 | 1234 | GLM 5 |
| Design Arena: data viz | 1243 | 1228 | Claude Opus 4.5 |
| Design Arena: 3D | 1214 | 1229 | GLM 5 |
| Design Arena: all code categories | 1242 | 1246 | GLM 5 |
| Design Arena: SVG | 1180 | 1168 | Claude Opus 4.5 |
| Design Arena: ASCII art | 1190 | 1146 | Claude Opus 4.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index182
| Benchmark | Claude Opus 4.5 | GLM 5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 52.1% | Not measured | Only Claude Opus 4.5 measured |
| MedScribe (Vals AI) | 85.3% | Not measured | Only Claude Opus 4.5 measured |
| IFBench | 58.0% | 72.3% | GLM 5 |
| Long context reasoning (AA-LCR) | 77.3% | 75.7% | Claude Opus 4.5 |
| DTBench | 89.9% | Not measured | Only Claude Opus 4.5 measured |
| LMCA | 44.5% | Not measured | Only Claude Opus 4.5 measured |
| CL-bench | 21.1% | 18.7% | Claude Opus 4.5 |
| Furniture assembly | 28.3% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text | 1451 | 1446 | Claude Opus 4.5 |
| LMArena Text: instruction following | 1478 | 1428 | Claude Opus 4.5 |
| LMArena Text: creative writing | 1445 | 1438 | Claude Opus 4.5 |
| LMArena Text: English | 1461 | 1458 | Claude Opus 4.5 |
| LMArena Text: non-English | 1438 | 1430 | Claude Opus 4.5 |
| LMArena Text: Chinese | 1470 | 1511 | GLM 5 |
| LMArena Text: German | 1449 | 1447 | Claude Opus 4.5 |
| LMArena Text: Japanese | 1417 | 1416 | Claude Opus 4.5 |
| LMArena Text: Korean | 1424 | 1423 | Claude Opus 4.5 |
| LMArena Text: French | 1471 | 1456 | Claude Opus 4.5 |
| LMArena Text: Spanish | 1457 | 1454 | Claude Opus 4.5 |
| LMArena Text: Russian | 1447 | 1436 | Claude Opus 4.5 |
| LMArena Text: Polish | 1439 | 1434 | Claude Opus 4.5 |
| LMArena Text: multi-turn | 1466 | 1456 | Claude Opus 4.5 |
| LMArena Text: longer queries | 1479 | 1446 | Claude Opus 4.5 |
| LMArena Text: writing and language | 1452 | 1437 | Claude Opus 4.5 |
| LMArena Text: entertainment and media | 1434 | 1426 | Claude Opus 4.5 |
| LMArena Document | 1462 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.5 | GLM 5 | 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 costs less
Repository review
50K input + 3K output tokens
GLM 5 costs less
Agent loop
200K input + 10K output tokens
GLM 5 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 Opus 4.5 | Z.ai GLM 5 |
|---|---|---|
| Maker | Anthropic | Z.ai |
| Weights | No public weights listed | Open weights |
| Released | November 24, 2025 | February 11, 2026 |
| Context window | 200K | 205K |
| Input $/Mtok | $5.00 | $1.00 |
| Output $/Mtok | $25.00 | $3.20 |
| Coding index | 66.8 | 59.7 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.37 | $0.63 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.5 better than GLM 5 for coding?
Pick Claude Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 59.7 for GLM 5. Pick GLM 5 when output tokens cost 7.8x less, or when a solved task costs $0.63 against $1.37.
Which is cheaper, Claude Opus 4.5 or GLM 5?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM 5 costs $1.00 and $3.20. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and GLM 5 $0.63.
Which has the bigger context window, Claude Opus 4.5 or GLM 5?
GLM 5, with 205K tokens against 200K.
How many benchmarks is the Claude Opus 4.5 vs GLM 5 comparison based on?
72 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.5's coding index rests on 2 independent benchmarks and GLM 5's on 2. Where only one model has a result, the page says so instead of naming a winner.