Model comparison
Amazon Nova Pro vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 31.0 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 categories and gpt-oss-120b in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 28.5.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 68.8% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | gpt-oss-120b | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 36.3 |
| Released | 2024-12-03 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 41K |
| Input $ / M tokens | $0.80 | $0.037 |
| Output $ / M tokens | $3.20 | $0.17 |
| Results tracked | 38 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), gpt-oss-120b: 33.5 (#256)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1270 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Amazon Nova Pro leads
Amazon Nova Pro: 16.7 (#147), gpt-oss-120b: 12.2 (#153)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning Too close to call
Amazon Nova Pro: 20.0 (#243), gpt-oss-120b: 20.0 (#245)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1364 |
| Epoch Capabilities Index | 123.8 | 139.93 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| LiveBench | 43.5% | — |
Math gpt-oss-120b leads
Amazon Nova Pro: 28.5 (#243), gpt-oss-120b: 52.5 (#50)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| Omni-MATH | 24.2% | 68.8% |
| LMArena Math | 1252 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LiveBench Math | 38% | — |
Knowledge gpt-oss-120b leads
Amazon Nova Pro: 27.4 (#250), gpt-oss-120b: 42.4 (#96)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| MMLU-Pro | 67.3% | 79.5% |
| Confabulations | 30.1% | 15.7% |
| Vectara Hallucination Rate | 5.1% | 14.2% |
| GPQA (HELM) | 44.6% | 68.4% |
| LMArena Expert | 1211 | 1356 |
| GPQA Diamond | — | 75.8% |
| Humanity's Last Exam | 4.4% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), gpt-oss-120b: —
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual gpt-oss-120b leads
Amazon Nova Pro: 39.7 (#223), gpt-oss-120b: 48.0 (#147)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1234 | 1351 |
| LMArena Chinese | 1244 | 1385 |
| LMArena French | 1271 | 1369 |
| LMArena German | 1243 | 1353 |
| LMArena Japanese | 1200 | 1331 |
| LMArena Korean | 1203 | 1282 |
| LMArena Russian | 1240 | 1343 |
| LMArena Spanish | 1182 | 1389 |
Instruction Following gpt-oss-120b leads
Amazon Nova Pro: 64.9 (#226), gpt-oss-120b: 69.3 (#173)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| IFEval | 81.5% | 83.6% |
| LMArena Instruction Following | 1235 | 1318 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), gpt-oss-120b: 31.4 (#278)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1255 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference gpt-oss-120b leads
Amazon Nova Pro: 43.9 (#226), gpt-oss-120b: 46.5 (#217)
| Benchmark | Amazon Nova Pro | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1259 | 1365 |
| LMArena Creative Writing | 1212 | 1275 |
| Short-Story Creative Writing | 60.5% | 77.1% |
| WildBench | 77.7% | 84.5% |
| LMArena Multi-Turn | 1246 | 1340 |
| EQ-Bench Creative Writing | — | 961 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro 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 Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or gpt-oss-120b better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Pro and gpt-oss-120b share?
26 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and gpt-oss-120b has 48.