Model comparison
GLM-4.5 vs Grok 3
GLM-4.5 is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GLM-4.5 scores higher in 4 categories and Grok 3 in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5 leads 27.7 to 13.8.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | Grok 3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 39.6 |
| Released | 2025-07-27 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 27 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.1 (#121), Grok 3: 41.5 (#113)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| WeirdML | 40.6% | 37.2% |
| LMArena Coding | 1434 | 1432 |
| SWE-bench Verified (bash only) | 54.2% | — |
| Aider Polyglot | — | 53.3% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Grok 3: 30.2 (#69)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| BALROG | — | 29.5% |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), Grok 3: 13.8 (#322)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 61.3% |
| LMArena Hard Prompts | 1430 | 1433 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| ARC-AGI-1 | — | 5.5% |
| Epoch Capabilities Index | — | 138.34 |
Math Too close to call
GLM-4.5: 36.3 (#119), Grok 3: 36.2 (#122)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| LMArena Math | 1427 | 1390 |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
GLM-4.5: 35.5 (#172), Grok 3: 46.0 (#76)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| Confabulations | 11.3% | 14.2% |
| LMArena Expert | 1433 | 1420 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 78.8% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
Multilingual Too close to call
GLM-4.5: 53.0 (#74), Grok 3: 52.5 (#81)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| LMArena Non-English | 1417 | 1411 |
| LMArena Chinese | 1465 | 1448 |
| LMArena French | 1423 | 1460 |
| LMArena German | 1406 | 1431 |
| LMArena Japanese | 1416 | 1389 |
| LMArena Korean | 1382 | 1374 |
| LMArena Russian | 1414 | 1416 |
| LMArena Spanish | 1454 | 1417 |
Instruction Following Too close to call
GLM-4.5: 74.3 (#100), Grok 3: 75.2 (#69)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1409 |
| IFEval | — | 88.4% |
Long Context Too close to call
GLM-4.5: 38.2 (#196), Grok 3: 38.7 (#187)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| Fiction.LiveBench | 58.3% | 58.3% |
| LMArena Longer Query | 1413 | 1439 |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.7 (#121), Grok 3: 56.0 (#136)
| Benchmark | GLM-4.5 | Grok 3 |
|---|---|---|
| LMArena Text | 1430 | 1426 |
| LMArena Creative Writing | 1395 | 1414 |
| Short-Story Creative Writing | 73.4% | 76.4% |
| EQ-Bench Creative Writing | 1343 | 1186 |
| LMArena Multi-Turn | 1415 | 1424 |
| WildBench | — | 84.9% |
Frequently asked questions
Is GLM-4.5 better than Grok 3?
GLM-4.5 is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index.
Is GLM-4.5 or Grok 3 better for coding?
They score almost the same on coding (41.1 vs 41.5); test both on your own repository before choosing.
How many benchmarks do GLM-4.5 and Grok 3 share?
23 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Grok 3 has 40.