Model comparison
Claude 3 Opus vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 29.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GLM-5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 80% for GLM-5.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | GLM-5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 29.5 | 46.1 |
| Released | 2024-02-29 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 46 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Claude 3 Opus: 32.9 (#267), GLM-5: 49.0 (#52)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| WeirdML | 19.2% | 48.2% |
| LMArena Coding | 1264 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 765.62 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use GLM-5 leads
Claude 3 Opus: 24.6 (#116), GLM-5: 31.1 (#71)
| Benchmark | Claude 3 Opus | 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 | 10% | — |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Claude 3 Opus: 14.6 (#324), GLM-5: 27.6 (#116)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| SimpleBench | 23.5% | 53.2% |
| Chess Puzzles | 5% | 10% |
| LMArena Hard Prompts | 1245 | 1452 |
| Epoch Capabilities Index | 126.91 | 145.83 |
| ForecastBench | 58.4 | 61 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math GLM-5 leads
Claude 3 Opus: 14.8 (#299), GLM-5: 46.4 (#71)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 80% |
| LMArena Math | 1273 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
Claude 3 Opus: 24.5 (#267), GLM-5: 52.3 (#64)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| GPQA Diamond | 47.2% | 87.8% |
| LMArena Expert | 1223 | 1454 |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 10.1% |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), GLM-5: —
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual GLM-5 leads
Claude 3 Opus: 41.4 (#207), GLM-5: 53.7 (#58)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| LMArena Non-English | 1258 | 1430 |
| LMArena Chinese | 1248 | 1511 |
| LMArena French | 1275 | 1455 |
| LMArena German | 1258 | 1445 |
| LMArena Japanese | 1204 | 1416 |
| LMArena Korean | 1187 | 1423 |
| LMArena Russian | 1280 | 1436 |
| LMArena Spanish | 1246 | 1454 |
Instruction Following GLM-5 leads
Claude 3 Opus: 64.1 (#228), GLM-5: 75.2 (#67)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1428 |
| LiveBench Instruction Following | 63.9% | — |
Long Context GLM-5 leads
Claude 3 Opus: 38.2 (#202), GLM-5: 44.7 (#60)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1259 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Claude 3 Opus: 47.2 (#213), GLM-5: 66.0 (#38)
| Benchmark | Claude 3 Opus | GLM-5 |
|---|---|---|
| LMArena Text | 1262 | 1446 |
| LMArena Creative Writing | 1235 | 1439 |
| LMArena Multi-Turn | 1275 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 29.5 on the Noometry Index.
Is Claude 3 Opus or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GLM-5 share?
24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GLM-5 has 45.