Model comparison
Claude Opus 4 vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 43.1 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude Opus 4 scores higher in 2 categories and GLM-5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 44.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 80% for GLM-5.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GLM-5 accepts more context: 205K tokens versus 200K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | GLM-5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 43.1 | 46.1 |
| Released | 2025-05-22 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 32K | 131K |
| Input $ / M tokens | $15 | $1 |
| Output $ / M tokens | $75 | $3.20 |
| Results tracked | 56 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Claude Opus 4: 47.2 (#62), GLM-5: 49.0 (#52)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| SWE-bench Verified | 70.7% | 72.1% |
| SWE-bench Verified (bash only) | 67.6% | 72.8% |
| WeirdML | 43.7% | 48.2% |
| LMArena Coding | 1442 | 1461 |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| GSO | 6.9% | — |
| ALE-Bench | — | 765.62 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), GLM-5: 31.1 (#71)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning Too close to call
Claude Opus 4: 27.3 (#121), GLM-5: 27.6 (#116)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| ARC-AGI-2 | 8.6% | 4.9% |
| SimpleBench | 58.8% | 53.2% |
| Kagi LLM Benchmark | 74.3% | 75% |
| ARC-AGI-1 | 35.7% | 44.7% |
| LMArena Hard Prompts | 1399 | 1452 |
| Epoch Capabilities Index | 142.67 | 145.83 |
| ForecastBench | 61.1 | 61 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 10% |
| EnigmaEval | 5.6% | — |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
Math GLM-5 leads
Claude Opus 4: 42.0 (#86), GLM-5: 46.4 (#71)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 80% |
| LMArena Math | 1390 | 1440 |
| FrontierMath (Feb 2025 set) | 4.5% | 16.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| MathArena Final-Answer Competitions | — | 65.7% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
Knowledge GLM-5 leads
Claude Opus 4: 44.0 (#88), GLM-5: 52.3 (#64)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| GPQA Diamond | 76.3% | 87.8% |
| Vectara Hallucination Rate | 12% | 10.1% |
| LMArena Expert | 1386 | 1454 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), GLM-5: —
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual GLM-5 leads
Claude Opus 4: 48.8 (#138), GLM-5: 53.7 (#58)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| LMArena Non-English | 1362 | 1430 |
| LMArena Chinese | 1386 | 1511 |
| LMArena French | 1372 | 1455 |
| LMArena German | 1391 | 1445 |
| LMArena Japanese | 1331 | 1416 |
| LMArena Korean | 1321 | 1423 |
| LMArena Russian | 1392 | 1436 |
| LMArena Spanish | 1389 | 1454 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), GLM-5: 75.2 (#67)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1428 |
| IFEval | 91.8% | — |
Long Context GLM-5 leads
Claude Opus 4: 39.6 (#172), GLM-5: 44.7 (#60)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1446 |
| Fiction.LiveBench | 61.1% | — |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Claude Opus 4: 61.2 (#89), GLM-5: 66.0 (#38)
| Benchmark | Claude Opus 4 | GLM-5 |
|---|---|---|
| LMArena Text | 1377 | 1446 |
| LMArena Creative Writing | 1387 | 1439 |
| EQ-Bench Creative Writing | 1580 | 1601 |
| LMArena Multi-Turn | 1396 | 1456 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or GLM-5?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 200K.
How many benchmarks do Claude Opus 4 and GLM-5 share?
32 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GLM-5 has 45.