Claude Opus 4.1 vs GLM 5.3
GLM 5.3 leads Claude Opus 4.1 on the Artificial Analysis Intelligence Index, 44.8 to 22.8, and GLM 5.3 costs 17.0x less per output token ($4.40 vs $75.00 per million). Updated October 22, 2026; 55 benchmarks have a result for both.
Claude Opus 4.1 or GLM 5.3: which to pick
Only GLM 5.3 has a coding score, 70.6 on the Vibe Coding Index; Claude Opus 4.1 has none, so the two cannot be ranked on coding.
Pick Claude Opus 4.1 for work measured by MMLU Pro or TaxEval (Vals AI), where it leads.
- Shared results
- 55
- Claude Opus 4.1 only
- 18
- GLM 5.3 only
- 45
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
No call
Only GLM 5.3 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GLM 5.3
GLM 5.3 leads, 44.8 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GLM 5.3 has a AA Agentic Index result, 53.1.
Directional only
Reasoning
GPQA Diamond
GLM 5.3
GLM 5.3 leads, 88.1% against 76.3%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.1 has a AIME result, 78.2%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.1
Claude Opus 4.1 leads, 87.9% against 86.8%.
Same board, both measured
Web design
Design Arena: websites
GLM 5.3
GLM 5.3 leads, 1295 against 1176.
Same board, both measured
General
Vals Index
No call
Only GLM 5.3 has a Vals Index result, 59.7%.
Directional only
Long documents
Listed context window
GLM 5.3
GLM 5.3 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5.3
Claude Opus 4.1 $0.052, GLM 5.3 $0.0036 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5.3 has the number, $0.36.
Directional only
At a glance
- Coding index
- Claude Opus 4.1 not benchmarked, GLM 5.3 70.6 from 6 benchmarks.
- Widest category
- Math, 25.3 points apart on average over 5 shared benchmarks.
- Widest single gap
- FrontierMath, tiers 1 to 3: Claude Opus 4.1 12.6% against GLM 5.3 68.8%, 56.1 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.1 $75.00 against GLM 5.3 $4.40 per million output tokens, 17.0x apart.
- Context window
- Claude Opus 4.1 takes 200K tokens, GLM 5.3 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 Opus 4.1 | Bars | GLM 5.3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 5 | ||
| Knowledge | 3 | 5 | ||
| Web design | 0 | 8 | ||
| General | 0 | 20 | ||
| All shared boards | 3 | 52 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 82.8% | Only GLM 5.3 measured |
| LMArena WebDev | 1390 | 1621 | GLM 5.3 |
| AA Coding Index | Not measured | 74.8 | Only GLM 5.3 measured |
| LiveCodeBench (Vals AI) | 66.5% | 80.5% | GLM 5.3 |
| SWE-bench Verified (Vals AI) | Not measured | 95.4% | Only GLM 5.3 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 38.9% | Only GLM 5.3 measured |
| Vibe Code Bench (Vals AI) | Not measured | 78.1% | Only GLM 5.3 measured |
| Code migration (Vals AI) | Not measured | 44.2% | Only GLM 5.3 measured |
| ProgramBench (Vals AI) | Not measured | 1.5% | Only GLM 5.3 measured |
| IOI (Vals AI) | Not measured | 68.4% | Only GLM 5.3 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 71.5% | Only GLM 5.3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 20.0% | Only GLM 5.3 measured |
| SkillsBench (Vals AI) | Not measured | 47.5% | Only GLM 5.3 measured |
| CyberBench (Vals AI) | Not measured | 72.1% | Only GLM 5.3 measured |
| SciCode | Not measured | 59.0% | Only GLM 5.3 measured |
| Terminal-Bench | 38.0% | Not measured | Only Claude Opus 4.1 measured |
| FrontierCode | Not measured | 40.1% | Only GLM 5.3 measured |
| FrontierSWE | Not measured | 30.2% | Only GLM 5.3 measured |
| WeirdML | 45.9% | 75.4% | GLM 5.3 |
| Cybench | 42.0% | Not measured | Only Claude Opus 4.1 measured |
| ALE-Bench | Not measured | 1317.4 | Only GLM 5.3 measured |
| LMArena Text: coding | 1479 | 1497 | GLM 5.3 |
| LMArena Text: software and IT | 1456 | 1493 | GLM 5.3 |
| LMArena WebDev: React | Not measured | 1641 | Only GLM 5.3 measured |
| LMArena WebDev: HTML | 1399 | 1595 | GLM 5.3 |
| SciCode | 4.6% | Not measured | Only Claude Opus 4.1 measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 44.8 | GLM 5.3 |
| Epoch Capabilities Index | 144.1 | 156.0 | GLM 5.3 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 53.1 | Only GLM 5.3 measured |
| Design Arena: agents building mobile apps | Not measured | 1194 | Only GLM 5.3 measured |
| Design Arena: HTML slides | Not measured | 1189 | Only GLM 5.3 measured |
| Design Arena: PowerPoint slides | Not measured | 1230 | Only GLM 5.3 measured |
| LiveBench research | Not measured | 73.2% | Only GLM 5.3 measured |
| LiveBench browser | Not measured | 0.0% | Only GLM 5.3 measured |
| LiveBench long agentic | Not measured | 35.9% | Only GLM 5.3 measured |
| SREBench (Vals AI) | Not measured | 9.2% | Only GLM 5.3 measured |
| Finance Agent (Vals AI) | Not measured | 55.8% | Only GLM 5.3 measured |
| Tax Agent Bench (Vals AI) | Not measured | 39.7% | Only GLM 5.3 measured |
| Legal Research Bench (Vals AI) | Not measured | 49.0% | Only GLM 5.3 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 14.6% | Only GLM 5.3 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 56.3% | Only GLM 5.3 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 5.7% | Only GLM 5.3 measured |
| APEX-Agents | Not measured | 56.6% | Only GLM 5.3 measured |
| METR time horizons | 66.8% | Not measured | Only Claude Opus 4.1 measured |
| GDPval | 43.6% | Not measured | Only Claude Opus 4.1 measured |
| DeepResearch Bench | 48.3% | Not measured | Only Claude Opus 4.1 measured |
| Vending-Bench 2 | Not measured | $8,164 | Only GLM 5.3 measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| GPQA Diamond | 76.3% | 88.1% | GLM 5.3 |
| LiveBench reasoning | Not measured | 85.8% | Only GLM 5.3 measured |
| MysteryMechanism (Vals AI) | Not measured | 23.0% | Only GLM 5.3 measured |
| MMMU Pro (Vals AI) | 77.5% | Not measured | Only Claude Opus 4.1 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 91.7% | Only GLM 5.3 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 42.3% | Only GLM 5.3 measured |
| GPQA Diamond (Epoch AI run) | 77.3% | 90.9% | GLM 5.3 |
| SimpleBench | 60.0% | Not measured | Only Claude Opus 4.1 measured |
| Chess puzzles | Not measured | 37.0% | Only GLM 5.3 measured |
| Mystery game puzzles | 21.0% | 33.0% | GLM 5.3 |
| EBR-bench | 7.9% | Not measured | Only Claude Opus 4.1 measured |
| VPCT | 35.0% | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text: hard prompts | 1442 | 1490 | GLM 5.3 |
| LMArena Text: expert | 1438 | 1514 | GLM 5.3 |
| LMArena Text: hard prompts in English | 1451 | 1496 | GLM 5.3 |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| AIME | 78.2% | Not measured | Only Claude Opus 4.1 measured |
| MATH 500 (Vals AI) | 95.4% | Not measured | Only Claude Opus 4.1 measured |
| MGSM (Vals AI) | 94.4% | Not measured | Only Claude Opus 4.1 measured |
| OTIS Mock AIME | 68.9% | 91.1% | GLM 5.3 |
| FrontierMath, tiers 1 to 3 | 12.6% | 68.8% | GLM 5.3 |
| FrontierMath, tier 4 | 2.4% | 29.3% | GLM 5.3 |
| ProofBench | Not measured | 49.0% | Only GLM 5.3 measured |
| LMArena Text: math | 1431 | 1495 | GLM 5.3 |
| LMArena Text: mathematical work | 1434 | 1497 | GLM 5.3 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index35
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| MMLU Pro | 87.9% | 86.8% | Claude Opus 4.1 |
| LegalBench (Vals AI) | 83.5% | 84.8% | GLM 5.3 |
| TaxEval (Vals AI) | 73.7% | 72.4% | Claude Opus 4.1 |
| MortgageTax (Vals AI) | 61.1% | Not measured | Only Claude Opus 4.1 measured |
| MedQA (Vals AI) | 93.6% | Not measured | Only Claude Opus 4.1 measured |
| MedCode (Vals AI) | 47.2% | 42.9% | Claude Opus 4.1 |
| SimpleQA Verified | Not measured | 41.0% | Only GLM 5.3 measured |
| LMArena Text: science | 1422 | 1498 | GLM 5.3 |
| LMArena Text: medicine and healthcare | 1416 | 1481 | GLM 5.3 |
| LMArena Text: legal and government | 1421 | 1473 | GLM 5.3 |
| LMArena Text: business and finance | 1406 | 1459 | GLM 5.3 |
| FACTS Benchmark Suite | 40.4% | Not measured | Only Claude Opus 4.1 measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1176 | 1295 | GLM 5.3 |
| Design Arena: UI components | 1162 | 1314 | GLM 5.3 |
| Design Arena: game dev | 1171 | 1311 | GLM 5.3 |
| Design Arena: data viz | 1166 | 1260 | GLM 5.3 |
| Design Arena: 3D | 1152 | 1332 | GLM 5.3 |
| Design Arena: all code categories | 1170 | 1304 | GLM 5.3 |
| Design Arena: SVG | 1152 | 1294 | GLM 5.3 |
| Design Arena: ASCII art | 1167 | 1208 | GLM 5.3 |
| LiveBench design | Not measured | 77.3% | Only GLM 5.3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
| Benchmark | Claude Opus 4.1 | GLM 5.3 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 59.7% | Only GLM 5.3 measured |
| LiveBench data analysis | Not measured | 70.2% | Only GLM 5.3 measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.5% | Only GLM 5.3 measured |
| SAGE (Vals AI) | 31.4% | Not measured | Only Claude Opus 4.1 measured |
| MedScribe (Vals AI) | 73.9% | 88.8% | GLM 5.3 |
| Long context reasoning (AA-LCR) | Not measured | 79.7% | Only GLM 5.3 measured |
| DTBench | 80.0% | 87.7% | GLM 5.3 |
| LMCA | 37.1% | 55.5% | GLM 5.3 |
| Creative writing (Lech Mazur) | 84.7% | Not measured | Only Claude Opus 4.1 measured |
| LMArena Text | 1419 | 1474 | GLM 5.3 |
| LMArena Text: instruction following | 1435 | 1479 | GLM 5.3 |
| LMArena Text: creative writing | 1412 | 1458 | GLM 5.3 |
| LMArena Text: English | 1433 | 1482 | GLM 5.3 |
| LMArena Text: non-English | 1405 | 1459 | GLM 5.3 |
| LMArena Text: Chinese | 1427 | 1532 | GLM 5.3 |
| LMArena Text: German | 1413 | 1488 | GLM 5.3 |
| LMArena Text: Japanese | 1377 | 1460 | GLM 5.3 |
| LMArena Text: Korean | 1381 | 1460 | GLM 5.3 |
| LMArena Text: French | 1433 | 1503 | GLM 5.3 |
| LMArena Text: Spanish | 1448 | 1462 | GLM 5.3 |
| LMArena Text: Russian | 1422 | 1469 | GLM 5.3 |
| LMArena Text: Polish | 1413 | 1466 | GLM 5.3 |
| LMArena Text: multi-turn | 1444 | 1472 | GLM 5.3 |
| LMArena Text: longer queries | 1455 | 1483 | GLM 5.3 |
| LMArena Text: writing and language | 1418 | 1469 | GLM 5.3 |
| LMArena Text: entertainment and media | 1398 | 1447 | GLM 5.3 |
| 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 4.1 | GLM 5.3 | 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 5.3 costs less
Repository review
50K input + 3K output tokens
GLM 5.3 costs less
Agent loop
200K input + 10K output tokens
GLM 5.3 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 4.1 | Z.ai GLM 5.3 |
|---|---|---|
| Maker | Anthropic | Z.ai |
| Weights | No public weights listed | Open weights |
| Released | August 5, 2025 | August 18, 2026 |
| Context window | 200K | 1.05M |
| Input $/Mtok | $15.00 | $1.40 |
| Output $/Mtok | $75.00 | $4.40 |
| Coding index | Not benchmarked | 70.6 |
| Independent measurements behind it | 1 | 6 |
| Cost per solved task | Not computable | $0.36 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.1 better than GLM 5.3 for coding?
Only GLM 5.3 has a coding score, 70.6 on the Vibe Coding Index; Claude Opus 4.1 has none, so the two cannot be ranked on coding. Pick Claude Opus 4.1 for work measured by MMLU Pro or TaxEval (Vals AI), where it leads.
Which is cheaper, Claude Opus 4.1 or GLM 5.3?
Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; GLM 5.3 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.3 only.
Which has the bigger context window, Claude Opus 4.1 or GLM 5.3?
GLM 5.3, with 1.05M tokens against 200K.
How many benchmarks is the Claude Opus 4.1 vs GLM 5.3 comparison based on?
55 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.1's coding index rests on 1 independent benchmark and GLM 5.3's on 6. Where only one model has a result, the page says so instead of naming a winner.