Model comparison
Amazon Nova Lite vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.0 to 31.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Amazon Nova Lite scores higher in 1 category and gpt-oss-120b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 25.8.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 68.8% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.06 / $0.24 for Amazon Nova Lite.
- Amazon Nova Lite accepts more context: 300K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | gpt-oss-120b | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.4 | 36.0 |
| Released | 2024-12-03 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 41K |
| Input $ / M tokens | $0.06 | $0.037 |
| Output $ / M tokens | $0.24 | $0.17 |
| Results tracked | 34 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
Amazon Nova Lite: 32.0 (#266), gpt-oss-120b: 33.2 (#251)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1239 | 1380 |
| ALE-Bench | 236.25 | 575.62 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| LiveBench Coding | 27.5% | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, gpt-oss-120b: 12.1 (#145)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning Too close to call
Amazon Nova Lite: 18.5 (#257), gpt-oss-120b: 19.5 (#236)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1364 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.94 |
| LiveBench | 36.4% | — |
Math gpt-oss-120b leads
Amazon Nova Lite: 25.8 (#243), gpt-oss-120b: 50.6 (#43)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| Omni-MATH | 23.3% | 68.8% |
| LMArena Math | 1227 | 1388 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LiveBench Math | 36.7% | — |
Knowledge gpt-oss-120b leads
Amazon Nova Lite: 26.0 (#254), gpt-oss-120b: 42.3 (#89)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| MMLU-Pro | 60% | 79.5% |
| Vectara Hallucination Rate | 6.1% | 14.2% |
| GPQA (HELM) | 39.7% | 68.4% |
| LMArena Expert | 1201 | 1356 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 3.6% | — |
| Confabulations | — | 15.7% |
| MMLU | 77% | — |
Multimodal Not comparable
Amazon Nova Lite: 25.0 (#118), gpt-oss-120b: —
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual gpt-oss-120b leads
Amazon Nova Lite: 38.2 (#227), gpt-oss-120b: 48.2 (#142)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1208 | 1350 |
| LMArena Chinese | 1225 | 1384 |
| LMArena French | 1237 | 1370 |
| LMArena German | 1229 | 1355 |
| LMArena Japanese | 1153 | 1332 |
| LMArena Korean | 1153 | 1283 |
| LMArena Russian | 1216 | 1343 |
| LMArena Spanish | 1225 | 1388 |
Instruction Following gpt-oss-120b leads
Amazon Nova Lite: 59.6 (#250), gpt-oss-120b: 69.5 (#168)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| IFEval | 77.6% | 83.6% |
| LMArena Instruction Following | 1205 | 1318 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#212), gpt-oss-120b: 31.4 (#273)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1234 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Amazon Nova Lite: 42.3 (#232), gpt-oss-120b: 46.7 (#213)
| Benchmark | Amazon Nova Lite | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1229 | 1366 |
| LMArena Creative Writing | 1197 | 1274 |
| WildBench | 75% | 84.5% |
| LMArena Multi-Turn | 1199 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.0 to 31.4 on the Noometry Index.
Which is cheaper, Amazon Nova Lite or gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Amazon Nova Lite lists at $0.06 and $0.24.
Is Amazon Nova Lite or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.2 versus 32.0 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Lite does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Lite and gpt-oss-120b share?
24 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and gpt-oss-120b has 48.