# Amazon Nova Pro vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 41.4 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-glm-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GLM-4.6 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 43.9.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 72.4% for GLM-4.6.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| Provider | Amazon | Z.ai (Zhipu) |
| Noometry Index | 31.0 | 41.4 |
| Rank | 281 | 135 |
| Context | 300K | 205K |
| Input $/M | $0.80 | $0.60 |
| Output $/M | $3.20 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- GLM-4.6: 40.1 (#148)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1270 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 340.82 |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- GLM-4.6: 32.3 (#66)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 72.4% |
| Terminal-Bench | — | 24.5% |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- GLM-4.6: 23.7 (#172)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- GLM-4.6: 39.1 (#111)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Math | 1252 | 1432 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- GLM-4.6: 40.2 (#124)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 9.5% |
| LMArena Expert | 1211 | 1431 |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- GLM-4.6: —

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- GLM-4.6: 53.5 (#66)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1234 | 1426 |
| LMArena Chinese | 1244 | 1499 |
| LMArena French | 1271 | 1459 |
| LMArena German | 1243 | 1447 |
| LMArena Japanese | 1200 | 1393 |
| LMArena Korean | 1203 | 1400 |
| LMArena Russian | 1240 | 1419 |
| LMArena Spanish | 1182 | 1436 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- GLM-4.6: 74.3 (#98)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1410 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- GLM-4.6: 43.4 (#94)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1255 | 1422 |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- GLM-4.6: 61.1 (#90)

| Benchmark | Amazon Nova Pro | GLM-4.6 |
|---|---|---|
| LMArena Text | 1259 | 1440 |
| LMArena Creative Writing | 1212 | 1411 |
| LMArena Multi-Turn | 1246 | 1427 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1411 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 31.0 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or GLM-4.6?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 205K.

### How many benchmarks do Amazon Nova Pro and GLM-4.6 share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GLM-4.6 has 29.