# GLM-4.5 vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 41.4 on the Noometry Index. GLM-4.5 costs 1.6× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-4.5 scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 27.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 75% for Grok 4.20 (Non-Reasoning).
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 48.5 |
| Rank | 125 | 48 |
| Context | 131K | 1M |
| Input $/M | $0.60 | $1.25 |
| Output $/M | $2.20 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.5: 41.1 (#121)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 40.6% | 52.3% |
| LMArena Coding | 1434 | 1458 |
| ALE-Bench | 344.82 | 1,150 |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1374 |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- GLM-4.5: 27.7 (#99)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 75% |
| LMArena Hard Prompts | 1430 | 1451 |
| ARC-AGI-2 | — | 65.1% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| Epoch Capabilities Index | — | 152.01 |
| ForecastBench | — | 61.4 |

## Math

- GLM-4.5: 36.3 (#119)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Math | 1427 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1433 | 1440 |
| GPQA Diamond | — | 89.3% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 30.2% |
| Confabulations | 11.3% | — |

## Multimodal

- GLM-4.5: —
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1417 | 1440 |
| LMArena Chinese | 1465 | 1481 |
| LMArena French | 1423 | 1477 |
| LMArena German | 1406 | 1463 |
| LMArena Japanese | 1416 | 1450 |
| LMArena Korean | 1382 | 1417 |
| LMArena Russian | 1414 | 1457 |
| LMArena Spanish | 1454 | 1442 |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1405 | 1420 |

## Long Context

- GLM-4.5: 38.2 (#196)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1413 | 1436 |
| Fiction.LiveBench | 58.3% | — |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | GLM-4.5 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1430 | 1451 |
| LMArena Creative Writing | 1395 | 1439 |
| EQ-Bench Creative Writing | 1343 | 1574 |
| LMArena Multi-Turn | 1415 | 1456 |
| Short-Story Creative Writing | 73.4% | — |

## FAQ

### Is GLM-4.5 better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 41.4 on the Noometry Index. GLM-4.5 costs 1.6× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

### Which is cheaper, GLM-4.5 or Grok 4.20 (Non-Reasoning)?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is GLM-4.5 or Grok 4.20 (Non-Reasoning) better for coding?

They score almost the same on coding (41.1 vs 41.8); test both on your own repository before choosing.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.

### How many benchmarks do GLM-4.5 and Grok 4.20 (Non-Reasoning) share?

21 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.