# Amazon Nova Micro vs gpt-oss-120b

> gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-micro-vs-gpt-oss-120b
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Amazon Nova Micro scores higher in 2 categories and gpt-oss-120b in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 26.9.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 68.8% for gpt-oss-120b.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.037 / $0.17 for gpt-oss-120b.
- gpt-oss-120b accepts more context: 131K tokens versus 128K.
- gpt-oss-120b has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.4 | 36.3 |
| Rank | 294 | 217 |
| Context | 128K | 131K |
| Input $/M | $0.035 | $0.037 |
| Output $/M | $0.14 | $0.17 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Micro: 30.5 (#295)
- gpt-oss-120b: 33.5 (#256)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1218 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |

## Agentic & Tool Use

- Amazon Nova Micro: 22.1 (#132)
- gpt-oss-120b: 12.2 (#153)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |

## Reasoning

- Amazon Nova Micro: 17.4 (#294)
- gpt-oss-120b: 20.0 (#245)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1364 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.93 |
| LiveBench | 29.6% | — |

## Math

- Amazon Nova Micro: 26.9 (#254)
- gpt-oss-120b: 52.5 (#50)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| Omni-MATH | 21.4% | 68.8% |
| LMArena Math | 1206 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LiveBench Math | 34.5% | — |

## Knowledge

- Amazon Nova Micro: 29.6 (#237)
- gpt-oss-120b: 42.4 (#96)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| MMLU-Pro | 51.1% | 79.5% |
| Vectara Hallucination Rate | 5.5% | 14.2% |
| GPQA (HELM) | 38.3% | 68.4% |
| LMArena Expert | 1184 | 1356 |
| GPQA Diamond | — | 75.8% |
| Confabulations | — | 15.7% |
| MMLU | 70.8% | — |

## Multilingual

- Amazon Nova Micro: 36.5 (#239)
- gpt-oss-120b: 48.0 (#147)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1186 | 1351 |
| LMArena Chinese | 1209 | 1385 |
| LMArena French | 1238 | 1369 |
| LMArena German | 1192 | 1353 |
| LMArena Japanese | 1154 | 1331 |
| LMArena Korean | 1150 | 1282 |
| LMArena Russian | 1185 | 1343 |
| LMArena Spanish | 1225 | 1389 |

## Instruction Following

- Amazon Nova Micro: 56.3 (#272)
- gpt-oss-120b: 69.3 (#173)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| IFEval | 76% | 83.6% |
| LMArena Instruction Following | 1174 | 1318 |
| LiveBench Instruction Following | 48% | — |

## Long Context

- Amazon Nova Micro: 36.5 (#229)
- gpt-oss-120b: 31.4 (#278)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1205 | 1319 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Amazon Nova Micro: 39.5 (#247)
- gpt-oss-120b: 46.5 (#217)

| Benchmark | Amazon Nova Micro | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1208 | 1365 |
| LMArena Creative Writing | 1172 | 1275 |
| WildBench | 74.3% | 84.5% |
| LMArena Multi-Turn | 1178 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| LiveBench Language | 15.8% | — |

## FAQ

### Is Amazon Nova Micro better than gpt-oss-120b?

gpt-oss-120b is the stronger model overall, scoring 36.3 to 30.4 on the Noometry Index.

### Which is cheaper, Amazon Nova Micro or gpt-oss-120b?

Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; gpt-oss-120b lists at $0.037 and $0.17.

### Is Amazon Nova Micro or gpt-oss-120b better for coding?

gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 30.5 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-120b does, with 131K tokens against 128K.

### How many benchmarks do Amazon Nova Micro and gpt-oss-120b share?

23 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and gpt-oss-120b has 48.