Model comparison
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.
Last verified . 23 shared benchmarks.
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.
Side by side
| Amazon Nova Micro | gpt-oss-120b | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.4 | 36.3 |
| Released | 2024-12-03 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 10K | 41K |
| Input $ / M tokens | $0.035 | $0.037 |
| Output $ / M tokens | $0.14 | $0.17 |
| Results tracked | 32 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
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 leads
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 gpt-oss-120b leads
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 gpt-oss-120b leads
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 gpt-oss-120b leads
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 gpt-oss-120b leads
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 gpt-oss-120b leads
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 leads
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 gpt-oss-120b leads
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% | — |
Frequently asked questions
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.