Model comparison
GLM-5.2 vs Grok 4.3
GLM-5.2 is the stronger model overall, scoring 51.1 to 43.8 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and Grok 4.3 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 58.5.
- The biggest single-benchmark swing is ProofBench: 35% for GLM-5.2 and 11% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | Grok 4.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 51.1 | 43.8 |
| Released | 2026-06-13 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 131K | 30K |
| Input $ / M tokens | $1.40 | $1.25 |
| Output $ / M tokens | $4.40 | $2.50 |
| Results tracked | 51 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Grok 4.3: 41.6 (#121)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1603 | 1357 |
| SciCode | 50.5% | 47.3% |
| WeirdML | 70.1% | 49.9% |
| LMArena Coding | 1485 | 1415 |
| ALE-Bench | 1,047 | 944.17 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
Agentic & Tool Use GLM-5.2 leads
GLM-5.2: 32.4 (#63), Grok 4.3: 27.7 (#99)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| Vending-Bench 2 | 8,314 | 35.26 |
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Grok 4.3: 35.9 (#68)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 74.3% | 55.2% |
| CritPt | 20.9% | 8% |
| Chess Puzzles | 21% | 25% |
| LMArena Hard Prompts | 1480 | 1396 |
| DTBench | 93.6% | 90.7% |
| LMCA | 45.8% | 38.3% |
| Epoch Capabilities Index | 151.78 | 149.16 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 60.3 |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Grok 4.3: 46.0 (#74)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 42.8% |
| FrontierMath Tier 4 | 29.3% | 14.6% |
| OTIS Mock AIME 2024-2025 | 86.4% | 93.3% |
| ProofBench | 35% | 11% |
| LMArena Math | 1482 | 1388 |
| MathArena Final-Answer Competitions | 67.6% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Grok 4.3: 52.5 (#62)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 91.9% | 88.8% |
| SimpleQA Verified | 34.2% | 33.2% |
| LMArena Expert | 1486 | 1385 |
Multimodal Not comparable
GLM-5.2: —, Grok 4.3: 31.6 (#104)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Grok 4.3: 50.5 (#120)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1459 | 1385 |
| LMArena Chinese | 1519 | 1422 |
| LMArena French | 1479 | 1412 |
| LMArena German | 1468 | 1395 |
| LMArena Japanese | 1451 | 1379 |
| LMArena Korean | 1445 | 1356 |
| LMArena Russian | 1466 | 1399 |
| LMArena Spanish | 1477 | 1398 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Grok 4.3: 72.1 (#140)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1366 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Grok 4.3: 42.5 (#123)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1479 | 1393 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Grok 4.3: 58.5 (#118)
| Benchmark | GLM-5.2 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1470 | 1397 |
| LMArena Creative Writing | 1462 | 1380 |
| EQ-Bench 4 | 1222 | 1075 |
| LMArena Multi-Turn | 1469 | 1406 |
| EQ-Bench Creative Writing | 1757 | — |
Frequently asked questions
Is GLM-5.2 better than Grok 4.3?
GLM-5.2 is the stronger model overall, scoring 51.1 to 43.8 on the Noometry Index.
Which is cheaper, GLM-5.2 or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Grok 4.3 better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do GLM-5.2 and Grok 4.3 share?
35 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Grok 4.3 has 40.