Model comparison
Claude 2 vs GLM-5
GLM-5 is the stronger model overall, scoring 46.1 to 25.0 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. Claude 2 scores higher in 0 categories and GLM-5 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 2 and 80% for GLM-5.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | GLM-5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 25.0 | 46.1 |
| Released | 2023-07-11 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 8 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, GLM-5: 49.0 (#52)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| LMArena Coding | — | 1461 |
| ALE-Bench | — | 765.62 |
| HumanEval+ | 61.6% | — |
Agentic & Tool Use Not comparable
Claude 2: —, GLM-5: 31.1 (#71)
| Benchmark | Claude 2 | 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% |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Claude 2: 21.7 (#216), GLM-5: 27.6 (#116)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| LMArena Hard Prompts | — | 1452 |
| DTBench | 51.9% | — |
| ForecastBench | — | 61 |
Math GLM-5 leads
Claude 2: 9.3 (#320), GLM-5: 46.4 (#71)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 80% |
| MathArena Final-Answer Competitions | — | 65.7% |
| LMArena Math | — | 1440 |
| MATH Level 5 | 11.7% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
Claude 2: 16.9 (#287), GLM-5: 52.3 (#64)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| GPQA Diamond | 34.7% | 87.8% |
| Vectara Hallucination Rate | — | 10.1% |
| LMArena Expert | — | 1454 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, GLM-5: 53.7 (#58)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1455 |
| LMArena German | — | 1445 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1423 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
Claude 2: —, GLM-5: 75.2 (#67)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| LMArena Instruction Following | — | 1428 |
Long Context Not comparable
Claude 2: —, GLM-5: 44.7 (#60)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| CL-bench | — | 18.7% |
| LMArena Longer Query | — | 1446 |
Writing & Preference Not comparable
Claude 2: —, GLM-5: 66.0 (#38)
| Benchmark | Claude 2 | GLM-5 |
|---|---|---|
| LMArena Text | — | 1446 |
| LMArena Creative Writing | — | 1439 |
| EQ-Bench Creative Writing | — | 1601 |
| LMArena Multi-Turn | — | 1456 |
Frequently asked questions
Is Claude 2 better than GLM-5?
GLM-5 is the stronger model overall, scoring 46.1 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and GLM-5 share?
3 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GLM-5 has 45.