Model comparison
GLM-4.5V vs Grok 4
Grok 4 is the stronger model overall, scoring 47.8 to 39.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. GLM-4.5V scores higher in 1 category and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 39.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 59.8% for GLM-4.5V and 73.6% for Grok 4.
- GLM-4.5V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5V | Grok 4 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 39.2 | 47.8 |
| Released | 2025-08-11 | 2025-07-09 |
| Weights | Open | Proprietary |
| Context window | 64K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $1.80 | — |
| Results tracked | 15 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
GLM-4.5V: 38.9 (#152), Grok 4: 49.9 (#44)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Coding | 1347 | 1408 |
| Aider Polyglot | — | 79.6% |
| WeirdML | — | 45.7% |
Agentic & Tool Use Not comparable
GLM-4.5V: —, Grok 4: 32.1 (#62)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
GLM-4.5V: 26.5 (#118), Grok 4: 36.9 (#59)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | 73.6% |
| LMArena Hard Prompts | 1335 | 1409 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| Epoch Capabilities Index | — | 146.46 |
| ForecastBench | — | 60.9 |
Math Grok 4 leads
GLM-4.5V: 34.7 (#157), Grok 4: 46.5 (#58)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Math | 1353 | 1422 |
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Grok 4 leads
GLM-4.5V: 36.8 (#155), Grok 4: 53.7 (#50)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Expert | 1353 | 1417 |
| GPQA Diamond | — | 87% |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
Multimodal Too close to call
GLM-4.5V: 33.6 (#86), Grok 4: 33.1 (#89)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Vision | 1154 | 1211 |
| GeoBench | — | 45% |
Multilingual Grok 4 leads
GLM-4.5V: 44.9 (#172), Grok 4: 52.0 (#98)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Non-English | 1304 | 1403 |
| LMArena Chinese | 1338 | 1428 |
| LMArena Russian | 1299 | 1409 |
| LMArena Spanish | 1335 | 1419 |
| LMArena French | — | 1418 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1396 |
| LMArena Korean | — | 1376 |
Instruction Following Grok 4 leads
GLM-4.5V: 69.4 (#170), Grok 4: 79.4 (#4)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1311 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
GLM-4.5V: 39.6 (#166), Grok 4: 63.1 (#4)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1305 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 leads
GLM-4.5V: 52.7 (#162), Grok 4: 58.7 (#111)
| Benchmark | GLM-4.5V | Grok 4 |
|---|---|---|
| LMArena Text | 1333 | 1412 |
| LMArena Creative Writing | 1295 | 1397 |
| LMArena Multi-Turn | 1333 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
Frequently asked questions
Is GLM-4.5V better than Grok 4?
Grok 4 is the stronger model overall, scoring 47.8 to 39.2 on the Noometry Index.
Is GLM-4.5V or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 49.9 versus 38.9 in the Noometry coding category.
How many benchmarks do GLM-4.5V and Grok 4 share?
15 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Grok 4 has 48.