Model comparison
Amazon Nova Micro vs GLM-4.7
GLM-4.7 is the stronger model overall, scoring 42.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 16× less per token, which makes it the better buy when GLM-4.7'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 Micro scores higher in 0 categories and GLM-4.7 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 60.9 to 39.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 11.7% for GLM-4.7.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 128K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | GLM-4.7 | |
|---|---|---|
| Provider | Amazon | Z.ai (Zhipu) |
| Noometry Index | 30.4 | 42.0 |
| Released | 2024-12-03 | 2025-12-22 |
| Weights | Proprietary | Open |
| Context window | 128K | 205K |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.035 | $0.60 |
| Output $ / M tokens | $0.14 | $2.20 |
| Results tracked | 32 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
Amazon Nova Micro: 30.5 (#295), GLM-4.7: 44.0 (#79)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Coding | 1218 | 1454 |
| LMArena WebDev | — | 1435 |
| SciCode | — | 45.1% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 399.48 |
Agentic & Tool Use GLM-4.7 leads
Amazon Nova Micro: 22.1 (#132), GLM-4.7: 26.5 (#103)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| Vending-Bench 2 | — | 2,377 |
Reasoning GLM-4.7 leads
Amazon Nova Micro: 17.4 (#294), GLM-4.7: 24.3 (#164)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1443 |
| SimpleBench | — | 47.7% |
| CritPt | — | 1.7% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 25.1% | — |
| LiveBench Data Analysis | 34% | — |
| Epoch Capabilities Index | — | 143.51 |
| LiveBench | 29.6% | — |
Math GLM-4.7 leads
Amazon Nova Micro: 26.9 (#254), GLM-4.7: 38.6 (#135)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Math | 1206 | 1423 |
| OTIS Mock AIME 2024-2025 | — | 83.3% |
| ProofBench | — | 6% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GLM-4.7 leads
Amazon Nova Micro: 29.6 (#237), GLM-4.7: 47.0 (#80)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 11.7% |
| LMArena Expert | 1184 | 1424 |
| GPQA Diamond | — | 83.3% |
| SimpleQA Verified | — | 32.2% |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual GLM-4.7 leads
Amazon Nova Micro: 36.5 (#239), GLM-4.7: 52.8 (#79)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1186 | 1417 |
| LMArena Chinese | 1209 | 1495 |
| LMArena French | 1238 | 1432 |
| LMArena German | 1192 | 1424 |
| LMArena Japanese | 1154 | 1439 |
| LMArena Korean | 1150 | 1399 |
| LMArena Russian | 1185 | 1423 |
| LMArena Spanish | 1225 | 1434 |
Instruction Following GLM-4.7 leads
Amazon Nova Micro: 56.3 (#272), GLM-4.7: 74.4 (#95)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1411 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context GLM-4.7 leads
Amazon Nova Micro: 36.5 (#229), GLM-4.7: 42.8 (#116)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1205 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference GLM-4.7 leads
Amazon Nova Micro: 39.5 (#247), GLM-4.7: 60.9 (#93)
| Benchmark | Amazon Nova Micro | GLM-4.7 |
|---|---|---|
| LMArena Text | 1208 | 1435 |
| LMArena Creative Writing | 1172 | 1401 |
| LMArena Multi-Turn | 1178 | 1446 |
| EQ-Bench Creative Writing | — | 1413 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than GLM-4.7?
GLM-4.7 is the stronger model overall, scoring 42.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 16× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or GLM-4.7?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is Amazon Nova Micro or GLM-4.7 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 128K.
How many benchmarks do Amazon Nova Micro and GLM-4.7 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and GLM-4.7 has 36.