Model comparison
Claude Opus 4.5 vs GLM-5.1
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.6 on the Noometry Index. GLM-5.1 costs 4.7× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and GLM-5.1 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 4.5 leads 47.2 to 24.8.
- The biggest single-benchmark swing is NYT Connections (extended): 52.5% for Claude Opus 4.5 and 77.7% for GLM-5.1.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.5 | GLM-5.1 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 50.5 | 47.6 |
| Released | 2025-11-01 | 2026-04-07 |
| Weights | Proprietary | Open |
| Context window | 200K | 200K |
| Max output | 64K | 131K |
| Input $ / M tokens | $5 | $1.40 |
| Output $ / M tokens | $25 | $4.40 |
| Results tracked | 69 | 41 |
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: 55.4 (#21), GLM-5.1: 48.5 (#52)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| SWE-bench Verified | 76.7% | 74.2% |
| LMArena WebDev | 1493 | 1509 |
| WeirdML | 63.7% | 57.1% |
| LMArena Coding | 1504 | 1486 |
| ALE-Bench | 1,025 | 887.1 |
| SWE-bench Verified (bash only) | 76.8% | — |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 43.8% |
| GSO | 26.5% | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.2 (#11), GLM-5.1: 24.8 (#106)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| Vending-Bench 2 | 4,967 | 5,634 |
| Terminal-Bench | 63.1% | — |
| APEX-Agents | — | 40.9% |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
Reasoning Claude Opus 4.5 leads
Claude Opus 4.5: 42.5 (#43), GLM-5.1: 38.2 (#57)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| SimpleBench | 62% | 55.1% |
| NYT Connections (extended) | 52.5% | 77.7% |
| Chess Puzzles | 12% | 19% |
| LMArena Hard Prompts | 1476 | 1472 |
| Epoch Capabilities Index | 150.1 | 149.86 |
| ARC-AGI-2 | 37.6% | — |
| Kagi LLM Benchmark | 80.2% | — |
| ARC-AGI-1 | 80% | — |
| CritPt | — | 4.6% |
| EnigmaEval | 11.9% | — |
| Thematic Generalization | — | 69.8% |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 22% | — |
| DTBench | 89.9% | — |
| LMCA | 44.5% | — |
| ForecastBench | 60.7 | — |
Math GLM-5.1 leads
Claude Opus 4.5: 38.5 (#85), GLM-5.1: 49.0 (#48)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 36.8% |
| OTIS Mock AIME 2024-2025 | 86.1% | 93.3% |
| ProofBench | 36% | 22.2% |
| LMArena Math | 1463 | 1472 |
| FrontierMath (Feb 2025 set) | 20.7% | 33.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 67.1% |
Knowledge Claude Opus 4.5 leads
Claude Opus 4.5: 56.4 (#38), GLM-5.1: 55.0 (#45)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 86% | 89.9% |
| SimpleQA Verified | 45.7% | 34% |
| LMArena Expert | 1488 | 1477 |
| Humanity's Last Exam | 25.2% | — |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
Claude Opus 4.5: 31.1 (#99), GLM-5.1: —
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |
Multilingual Too close to call
Claude Opus 4.5: 54.5 (#45), GLM-5.1: 55.2 (#34)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1438 | 1448 |
| LMArena Chinese | 1470 | 1516 |
| LMArena French | 1471 | 1478 |
| LMArena German | 1449 | 1466 |
| LMArena Japanese | 1415 | 1436 |
| LMArena Korean | 1424 | 1423 |
| LMArena Russian | 1448 | 1453 |
| LMArena Spanish | 1455 | 1467 |
Instruction Following Claude Opus 4.5 leads
Claude Opus 4.5: 77.7 (#20), GLM-5.1: 76.5 (#41)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1451 |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.4 (#21), GLM-5.1: 44.9 (#51)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1480 | 1467 |
| CL-bench | 21.1% | — |
Writing & Preference Claude Opus 4.5 leads
Claude Opus 4.5: 68.2 (#28), GLM-5.1: 67.2 (#29)
| Benchmark | Claude Opus 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1451 | 1462 |
| LMArena Creative Writing | 1445 | 1454 |
| EQ-Bench Creative Writing | 1687 | 1592 |
| LMArena Multi-Turn | 1466 | 1473 |
Frequently asked questions
Is Claude Opus 4.5 better than GLM-5.1?
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 47.6 on the Noometry Index. GLM-5.1 costs 4.7× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.5 or GLM-5.1?
GLM-5.1 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-5.1 better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 48.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Opus 4.5 and GLM-5.1 share?
34 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and GLM-5.1 has 41.