Model comparison
Claude Opus 4.5 vs GLM-5.2
Claude Opus 4.5 and GLM-5.2 score almost the same on the Noometry Index (50.5 vs 51.1), so choose on price, context window or the category you care about most.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and GLM-5.2 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.7 to 38.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 34.4% for Claude Opus 4.5 and 59.2% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- GLM-5.2 accepts more context: 1M tokens versus 200K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.5 | GLM-5.2 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 50.5 | 51.1 |
| Released | 2025-11-01 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | 200K | 1M |
| Max output | 64K | 131K |
| Input $ / M tokens | $5 | $1.40 |
| Output $ / M tokens | $25 | $4.40 |
| Results tracked | 69 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.5 leads
Claude Opus 4.5: 54.8 (#27), GLM-5.2: 51.3 (#41)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| SWE-bench Verified | 76.7% | 78.7% |
| LMArena WebDev | 1494 | 1603 |
| WeirdML | 63.7% | 70.1% |
| LMArena Coding | 1504 | 1485 |
| ALE-Bench | 1,025 | 1,047 |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| SWE-bench Verified (bash only) | 76.8% | — |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 50.5% |
| GSO | 26.5% | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.3 (#12), GLM-5.2: 32.4 (#63)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| τ²-bench Banking | 24.7% | 37.1% |
| Vending-Bench 2 | 4,967 | 8,314 |
| Terminal-Bench | 63.1% | — |
| APEX-Agents | — | 45.2% |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| PostTrainBench | — | 31.7% |
| BALROG | 43.5% | — |
| GBAEval | — | 0% |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
Reasoning Too close to call
Claude Opus 4.5: 42.6 (#51), GLM-5.2: 42.3 (#52)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| ARC-AGI-2 | 37.6% | 22.8% |
| SimpleBench | 62% | 58.8% |
| Kagi LLM Benchmark | 80.2% | 62.6% |
| NYT Connections (extended) | 52.5% | 74.3% |
| ARC-AGI-1 | 80% | 77% |
| Chess Puzzles | 12% | 21% |
| EBR-Bench | 14.3% | 9.5% |
| LMArena Hard Prompts | 1476 | 1480 |
| Mystery Game Puzzles | 22% | 19% |
| DTBench | 89.9% | 93.6% |
| LMCA | 44.5% | 45.8% |
| Epoch Capabilities Index | 150.09 | 151.78 |
| CritPt | — | 20.9% |
| EnigmaEval | 11.9% | — |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 60.7 | — |
Math GLM-5.2 leads
Claude Opus 4.5: 38.6 (#132), GLM-5.2: 55.7 (#43)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 59.2% |
| FrontierMath Tier 4 | 4.9% | 29.3% |
| OTIS Mock AIME 2024-2025 | 86.1% | 86.4% |
| ProofBench | 36% | 35% |
| LMArena Math | 1463 | 1482 |
| MathArena Final-Answer Competitions | — | 67.6% |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Claude Opus 4.5: 56.5 (#44), GLM-5.2: 57.1 (#40)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 86% | 91.9% |
| SimpleQA Verified | 45.7% | 34.2% |
| LMArena Expert | 1487 | 1486 |
| Humanity's Last Exam | 25.2% | — |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
Claude Opus 4.5: 31.4 (#107), GLM-5.2: —
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |
Multilingual GLM-5.2 leads
Claude Opus 4.5: 54.3 (#47), GLM-5.2: 55.8 (#26)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1438 | 1459 |
| LMArena Chinese | 1470 | 1519 |
| LMArena French | 1471 | 1479 |
| LMArena German | 1449 | 1468 |
| LMArena Japanese | 1416 | 1451 |
| LMArena Korean | 1424 | 1445 |
| LMArena Russian | 1447 | 1466 |
| LMArena Spanish | 1458 | 1477 |
Instruction Following Too close to call
Claude Opus 4.5: 77.5 (#19), GLM-5.2: 76.9 (#34)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1465 |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.5 (#22), GLM-5.2: 45.3 (#43)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1480 | 1479 |
| CL-bench | 21.1% | — |
Writing & Preference GLM-5.2 leads
Claude Opus 4.5: 68.1 (#28), GLM-5.2: 70.4 (#21)
| Benchmark | Claude Opus 4.5 | GLM-5.2 |
|---|---|---|
| LMArena Text | 1451 | 1470 |
| LMArena Creative Writing | 1445 | 1462 |
| EQ-Bench Creative Writing | 1687 | 1757 |
| LMArena Multi-Turn | 1466 | 1469 |
| EQ-Bench 4 | — | 1222 |
Frequently asked questions
Is Claude Opus 4.5 better than GLM-5.2?
Claude Opus 4.5 and GLM-5.2 score almost the same on the Noometry Index (50.5 vs 51.1), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Opus 4.5 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 Opus 4.5 lists at $5 and $25.
Is Claude Opus 4.5 or GLM-5.2 better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 4.5 and GLM-5.2 share?
41 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and GLM-5.2 has 51.