Model comparison
Claude Opus 4 vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Opus 4 scores higher in 2 categories and GLM-5.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 27.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 93.3% for GLM-5.1.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | GLM-5.1 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 43.1 | 47.8 |
| Released | 2025-05-22 | 2026-04-07 |
| Weights | Proprietary | Open |
| Context window | 200K | 200K |
| Max output | 32K | 131K |
| Input $ / M tokens | $15 | $1.40 |
| Output $ / M tokens | $75 | $4.40 |
| Results tracked | 56 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Claude Opus 4: 47.2 (#62), GLM-5.1: 48.7 (#55)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| SWE-bench Verified | 70.7% | 74.2% |
| WeirdML | 43.7% | 57.1% |
| LMArena Coding | 1442 | 1485 |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1508 |
| SciCode | — | 43.8% |
| GSO | 6.9% | — |
| ALE-Bench | — | 887.1 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), GLM-5.1: 24.9 (#113)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| APEX-Agents | — | 40.9% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
Claude Opus 4: 27.3 (#121), GLM-5.1: 39.1 (#60)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| SimpleBench | 58.8% | 55.1% |
| CritPt | 0.3% | 4.6% |
| LMArena Hard Prompts | 1399 | 1472 |
| Epoch Capabilities Index | 142.67 | 149.84 |
| ARC-AGI-2 | 8.6% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 77.7% |
| ARC-AGI-1 | 35.7% | — |
| Chess Puzzles | — | 19% |
| EnigmaEval | 5.6% | — |
| Thematic Generalization | — | 69.8% |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| ForecastBench | 61.1 | — |
Math GLM-5.1 leads
Claude Opus 4: 42.0 (#86), GLM-5.1: 49.7 (#60)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 93.3% |
| LMArena Math | 1390 | 1473 |
| FrontierMath (Feb 2025 set) | 4.5% | 33.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| ProofBench | — | 22.2% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
Knowledge GLM-5.1 leads
Claude Opus 4: 44.0 (#88), GLM-5.1: 54.9 (#50)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 76.3% | 89.9% |
| LMArena Expert | 1386 | 1476 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 34% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), GLM-5.1: —
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual GLM-5.1 leads
Claude Opus 4: 48.8 (#138), GLM-5.1: 55.0 (#36)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1362 | 1447 |
| LMArena Chinese | 1386 | 1515 |
| LMArena French | 1372 | 1474 |
| LMArena German | 1391 | 1465 |
| LMArena Japanese | 1331 | 1434 |
| LMArena Korean | 1321 | 1418 |
| LMArena Russian | 1392 | 1454 |
| LMArena Spanish | 1389 | 1469 |
Instruction Following Too close to call
Claude Opus 4: 77.1 (#28), GLM-5.1: 76.3 (#42)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1451 |
| IFEval | 91.8% | — |
Long Context GLM-5.1 leads
Claude Opus 4: 39.6 (#172), GLM-5.1: 44.9 (#53)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1466 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference GLM-5.1 leads
Claude Opus 4: 61.2 (#89), GLM-5.1: 66.9 (#31)
| Benchmark | Claude Opus 4 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1377 | 1461 |
| LMArena Creative Writing | 1387 | 1453 |
| EQ-Bench Creative Writing | 1580 | 1592 |
| LMArena Multi-Turn | 1396 | 1472 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 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 lists at $15 and $75.
Is Claude Opus 4 or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Opus 4 and GLM-5.1 share?
27 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GLM-5.1 has 41.