# GLM-5.2 vs Grok 4.20 (Non-Reasoning)

> GLM-5.2 is the stronger model overall, scoring 51.1 to 48.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. GLM-5.2 scores higher in 6 categories and Grok 4.20 (Non-Reasoning) in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 42.3.
- The biggest single-benchmark swing is ARC-AGI-2: 22.8% for GLM-5.2 and 65.1% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) 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.

## Snapshot

| | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 51.1 | 48.6 |
| Rank | 44 | 54 |
| Context | 1M | 1M |
| Input $/M | $1.40 | $1.25 |
| Output $/M | $4.40 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.2: 51.3 (#41)
- Grok 4.20 (Non-Reasoning): 42.1 (#112)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1603 | 1375 |
| WeirdML | 70.1% | 52.3% |
| LMArena Coding | 1485 | 1459 |
| ALE-Bench | 1,047 | 1,150 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SciCode | 50.5% | — |

## Agentic & Tool Use

- GLM-5.2: 32.4 (#63)
- Grok 4.20 (Non-Reasoning): 34.4 (#46)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| τ²-bench Banking | 37.1% | 18% |
| Vending-Bench 2 | 8,314 | 4,663 |
| Terminal-Bench | — | 57.3% |
| APEX-Agents | 45.2% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| LMArena Search | — | 1189 |

## Reasoning

- GLM-5.2: 42.3 (#52)
- Grok 4.20 (Non-Reasoning): 52.3 (#32)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 22.8% | 65.1% |
| Kagi LLM Benchmark | 62.6% | 75% |
| NYT Connections (extended) | 74.3% | 85.4% |
| ARC-AGI-1 | 77% | 89.5% |
| Chess Puzzles | 21% | 24% |
| LMArena Hard Prompts | 1480 | 1451 |
| DTBench | 93.6% | 90.1% |
| LMCA | 45.8% | 38.7% |
| Epoch Capabilities Index | 151.78 | 151.98 |
| SimpleBench | 58.8% | — |
| CritPt | 20.9% | — |
| Thematic Generalization | — | 63.8% |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 61.4 |

## Math

- GLM-5.2: 55.7 (#43)
- Grok 4.20 (Non-Reasoning): 48.2 (#65)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 44.9% |
| FrontierMath Tier 4 | 29.3% | 17.1% |
| OTIS Mock AIME 2024-2025 | 86.4% | 92.2% |
| ProofBench | 35% | 14% |
| LMArena Math | 1482 | 1455 |
| MathArena Final-Answer Competitions | 67.6% | — |

## Knowledge

- GLM-5.2: 57.1 (#40)
- Grok 4.20 (Non-Reasoning): 52.8 (#60)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 91.9% | 89.3% |
| SimpleQA Verified | 34.2% | 30.2% |
| LMArena Expert | 1486 | 1439 |

## Multimodal

- GLM-5.2: —
- Grok 4.20 (Non-Reasoning): 33.3 (#98)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- GLM-5.2: 55.8 (#26)
- Grok 4.20 (Non-Reasoning): 54.5 (#40)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1459 | 1441 |
| LMArena Chinese | 1519 | 1481 |
| LMArena French | 1479 | 1476 |
| LMArena German | 1468 | 1465 |
| LMArena Japanese | 1451 | 1449 |
| LMArena Korean | 1445 | 1417 |
| LMArena Russian | 1466 | 1458 |
| LMArena Spanish | 1477 | 1443 |

## Instruction Following

- GLM-5.2: 76.9 (#34)
- Grok 4.20 (Non-Reasoning): 74.8 (#83)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1465 | 1420 |

## Long Context

- GLM-5.2: 45.3 (#43)
- Grok 4.20 (Non-Reasoning): 45.5 (#34)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1479 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- GLM-5.2: 70.4 (#21)
- Grok 4.20 (Non-Reasoning): 65.7 (#44)

| Benchmark | GLM-5.2 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1470 | 1451 |
| LMArena Creative Writing | 1462 | 1438 |
| EQ-Bench Creative Writing | 1757 | 1574 |
| LMArena Multi-Turn | 1469 | 1456 |
| EQ-Bench 4 | 1222 | — |

## FAQ

### Is GLM-5.2 better than Grok 4.20 (Non-Reasoning)?

GLM-5.2 is the stronger model overall, scoring 51.1 to 48.6 on the Noometry Index.

### Which is cheaper, GLM-5.2 or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) 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 4.20 (Non-Reasoning) better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 42.1 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do GLM-5.2 and Grok 4.20 (Non-Reasoning) share?

37 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.