Model comparison
gpt-oss-120b vs Nova 2 Lite
Nova 2 Lite is the stronger model overall, scoring 39.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Nova 2 Lite in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 37.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 14.2% for gpt-oss-120b and 5.1% for Nova 2 Lite.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- Nova 2 Lite accepts more context: 1M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Nova 2 Lite | |
|---|---|---|
| Provider | OpenAI | Amazon |
| Noometry Index | 36.3 | 39.7 |
| Released | 2025-08-05 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 41K | 64K |
| Input $ / M tokens | $0.037 | $0.30 |
| Output $ / M tokens | $0.17 | $2.50 |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
gpt-oss-120b: 33.5 (#256), Nova 2 Lite: 40.7 (#134)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1380 | 1385 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Nova 2 Lite leads
gpt-oss-120b: 12.2 (#153), Nova 2 Lite: 24.1 (#121)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Nova 2 Lite leads
gpt-oss-120b: 20.0 (#245), Nova 2 Lite: 27.5 (#118)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1364 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Nova 2 Lite: 37.5 (#156)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1389 | 1359 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge Too close to call
gpt-oss-120b: 42.4 (#96), Nova 2 Lite: 43.0 (#94)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 14.2% | 5.1% |
| LMArena Expert | 1356 | 1358 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual Too close to call
gpt-oss-120b: 48.0 (#147), Nova 2 Lite: 47.1 (#153)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1351 | 1337 |
| LMArena Chinese | 1385 | 1364 |
| LMArena French | 1369 | 1381 |
| LMArena German | 1353 | 1343 |
| LMArena Japanese | 1331 | 1271 |
| LMArena Korean | 1282 | 1284 |
| LMArena Russian | 1343 | 1343 |
| LMArena Spanish | 1389 | 1373 |
Instruction Following Nova 2 Lite leads
gpt-oss-120b: 69.3 (#173), Nova 2 Lite: 70.5 (#161)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1318 | 1335 |
| IFEval | 83.6% | — |
Long Context Nova 2 Lite leads
gpt-oss-120b: 31.4 (#278), Nova 2 Lite: 40.6 (#150)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1319 | 1335 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Nova 2 Lite leads
gpt-oss-120b: 46.5 (#217), Nova 2 Lite: 53.9 (#154)
| Benchmark | gpt-oss-120b | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1365 | 1362 |
| LMArena Creative Writing | 1275 | 1291 |
| LMArena Multi-Turn | 1340 | 1338 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Nova 2 Lite?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Nova 2 Lite?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is gpt-oss-120b or Nova 2 Lite better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-120b and Nova 2 Lite share?
18 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Nova 2 Lite has 19.