Model comparison
Amazon Nova Lite vs gpt-oss-20b
Amazon Nova Lite and gpt-oss-20b score almost the same on the Noometry Index (31.9 vs 32.5), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Amazon Nova Lite scores higher in 2 categories and gpt-oss-20b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 27.8.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 56.5% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 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-20b has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | gpt-oss-20b | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.9 | 32.5 |
| Released | 2024-12-03 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.06 | $0.018 |
| Output $ / M tokens | $0.24 | $0.09 |
| Results tracked | 34 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Amazon Nova Lite: 32.5 (#270), gpt-oss-20b: 37.6 (#192)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1239 | 1306 |
| ALE-Bench | 236.25 | 566.05 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| LiveBench Coding | 27.5% | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Too close to call
Amazon Nova Lite: 19.3 (#260), gpt-oss-20b: 19.3 (#261)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1274 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 68% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
| LiveBench | 36.4% | — |
Math gpt-oss-20b leads
Amazon Nova Lite: 27.8 (#247), gpt-oss-20b: 39.4 (#103)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| Omni-MATH | 23.3% | 56.5% |
| LMArena Math | 1227 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| LiveBench Math | 36.7% | — |
Knowledge gpt-oss-20b leads
Amazon Nova Lite: 26.3 (#259), gpt-oss-20b: 34.6 (#195)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| MMLU-Pro | 60% | 74% |
| GPQA (HELM) | 39.7% | 59.4% |
| LMArena Expert | 1201 | 1258 |
| GPQA Diamond | — | 60.8% |
| Humanity's Last Exam | 3.6% | — |
| Vectara Hallucination Rate | 6.1% | — |
| MMLU | 77% | — |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), gpt-oss-20b: —
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual gpt-oss-20b leads
Amazon Nova Lite: 38.0 (#232), gpt-oss-20b: 42.2 (#197)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1208 | 1268 |
| LMArena Chinese | 1225 | 1314 |
| LMArena German | 1229 | 1255 |
| LMArena Japanese | 1153 | 1244 |
| LMArena Korean | 1153 | 1236 |
| LMArena Russian | 1216 | 1278 |
| LMArena Spanish | 1226 | 1267 |
| LMArena French | 1237 | — |
Instruction Following gpt-oss-20b leads
Amazon Nova Lite: 59.3 (#255), gpt-oss-20b: 61.8 (#240)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| IFEval | 77.6% | 73.2% |
| LMArena Instruction Following | 1205 | 1236 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Too close to call
Amazon Nova Lite: 37.4 (#217), gpt-oss-20b: 37.9 (#209)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1234 | 1250 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), gpt-oss-20b: 35.5 (#265)
| Benchmark | Amazon Nova Lite | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1229 | 1287 |
| LMArena Creative Writing | 1197 | 1201 |
| WildBench | 75% | 73.7% |
| LMArena Multi-Turn | 1199 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than gpt-oss-20b?
Amazon Nova Lite and gpt-oss-20b score almost the same on the Noometry Index (31.9 vs 32.5), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Lite or gpt-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Amazon Nova Lite lists at $0.06 and $0.24.
Is Amazon Nova Lite or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 32.5 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-20b share?
22 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and gpt-oss-20b has 34.