Model comparison
Amazon Nova Pro vs GLM-5.3
GLM-5.3 is the stronger model overall, scoring 54.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 1.5× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GLM-5.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3 leads 62.3 to 28.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
- GLM-5.3 accepts more context: 1M tokens versus 300K.
- GLM-5.3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | GLM-5.3 | |
|---|---|---|
| Provider | Amazon | Z.ai (Zhipu) |
| Noometry Index | 31.0 | 54.8 |
| Released | 2024-12-03 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 300K | 1M |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.80 | $1.40 |
| Output $ / M tokens | $3.20 | $4.40 |
| Results tracked | 38 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3 leads
Amazon Nova Pro: 35.1 (#229), GLM-5.3: 59.5 (#14)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Coding | 1270 | 1496 |
| DeepSWE | — | 69% |
| FrontierCode | — | 40.1% |
| CursorBench | — | 42.6% |
| LMArena WebDev | — | 1622 |
| FrontierSWE | — | 30.2% |
| SciCode | — | 59% |
| WeirdML | — | 75.4% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,317 |
Agentic & Tool Use GLM-5.3 leads
Amazon Nova Pro: 16.7 (#147), GLM-5.3: 36.4 (#38)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| APEX-Agents | — | 56.6% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Vending-Bench 2 | — | 8,164 |
Reasoning GLM-5.3 leads
Amazon Nova Pro: 20.0 (#243), GLM-5.3: 46.1 (#46)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1489 |
| Epoch Capabilities Index | 123.8 | 155.61 |
| NYT Connections (extended) | — | 74.2% |
| CritPt | — | 19.1% |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 33% |
| DTBench | — | 87.7% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 55.5% |
| Bench to the Future 3 | — | 0.15 |
| LiveBench | 43.5% | — |
Math GLM-5.3 leads
Amazon Nova Pro: 28.5 (#243), GLM-5.3: 62.3 (#33)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Math | 1252 | 1489 |
| FrontierMath (Tiers 1-3) | — | 68.8% |
| FrontierMath Tier 4 | — | 29.3% |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| ProofBench | — | 49% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge GLM-5.3 leads
Amazon Nova Pro: 27.4 (#250), GLM-5.3: 58.3 (#37)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Expert | 1211 | 1516 |
| GPQA Diamond | — | 90.9% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 41% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), GLM-5.3: —
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual GLM-5.3 leads
Amazon Nova Pro: 39.7 (#223), GLM-5.3: 55.7 (#28)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Non-English | 1234 | 1457 |
| LMArena Chinese | 1244 | 1528 |
| LMArena French | 1271 | 1499 |
| LMArena German | 1243 | 1499 |
| LMArena Japanese | 1200 | 1453 |
| LMArena Korean | 1203 | 1472 |
| LMArena Russian | 1240 | 1463 |
| LMArena Spanish | 1182 | 1460 |
Instruction Following GLM-5.3 leads
Amazon Nova Pro: 64.9 (#226), GLM-5.3: 77.5 (#23)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Instruction Following | 1235 | 1477 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context GLM-5.3 leads
Amazon Nova Pro: 38.1 (#205), GLM-5.3: 45.4 (#41)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Longer Query | 1255 | 1482 |
Writing & Preference GLM-5.3 leads
Amazon Nova Pro: 43.9 (#226), GLM-5.3: 75.7 (#6)
| Benchmark | Amazon Nova Pro | GLM-5.3 |
|---|---|---|
| LMArena Text | 1259 | 1471 |
| LMArena Creative Writing | 1212 | 1457 |
| LMArena Multi-Turn | 1246 | 1472 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 2075 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GLM-5.3?
GLM-5.3 is the stronger model overall, scoring 54.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 1.5× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or GLM-5.3?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.
Is Amazon Nova Pro or GLM-5.3 better for coding?
GLM-5.3 scores higher on coding benchmarks: 59.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3 does, with 1M tokens against 300K.
How many benchmarks do Amazon Nova Pro and GLM-5.3 share?
18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GLM-5.3 has 42.