Model comparison
GPT-4.1 nano vs gpt-oss-120b
gpt-oss-120b is the stronger model overall, scoring 36.3 to 27.9 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GPT-4.1 nano scores higher in 1 category and gpt-oss-120b in 8 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 OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 88.9% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.10 / $0.40 for GPT-4.1 nano.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 nano | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.9 | 36.3 |
| Released | 2025-04-14 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 33K | 41K |
| Input $ / M tokens | $0.10 | $0.037 |
| Output $ / M tokens | $0.40 | $0.17 |
| Results tracked | 38 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-120b leads
GPT-4.1 nano: 24.1 (#330), gpt-oss-120b: 33.5 (#256)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| Aider Polyglot | 8.9% | 41.8% |
| SciCode | 25.9% | 36% |
| WeirdML | 19% | 48.2% |
| LMArena Coding | 1306 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GPT-4.1 nano leads
GPT-4.1 nano: 26.5 (#104), gpt-oss-120b: 12.2 (#153)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 33% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
GPT-4.1 nano: 8.5 (#349), gpt-oss-120b: 20.0 (#245)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| Kagi LLM Benchmark | 33.3% | 58.6% |
| CritPt | 0% | 1.1% |
| LMArena Hard Prompts | 1286 | 1364 |
| DTBench | 52.5% | 76.3% |
| LMCA | 5.5% | 22.1% |
| Epoch Capabilities Index | 129.62 | 139.93 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 22.1% |
| ARC-AGI-1 | 0% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 2% |
| Surface Evolver Bench | — | 25% |
Math gpt-oss-120b leads
GPT-4.1 nano: 26.9 (#252), gpt-oss-120b: 52.5 (#50)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 88.9% |
| Omni-MATH | 36.7% | 68.8% |
| LMArena Math | 1274 | 1389 |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge gpt-oss-120b leads
GPT-4.1 nano: 21.8 (#273), gpt-oss-120b: 42.4 (#96)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 48.9% | 75.8% |
| MMLU-Pro | 55% | 79.5% |
| GPQA (HELM) | 50.7% | 68.4% |
| LMArena Expert | 1272 | 1356 |
| SimpleQA Verified | 6% | — |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), gpt-oss-120b: —
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual gpt-oss-120b leads
GPT-4.1 nano: 41.6 (#205), gpt-oss-120b: 48.0 (#147)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1260 | 1351 |
| LMArena Chinese | 1270 | 1385 |
| LMArena German | 1288 | 1353 |
| LMArena Japanese | 1198 | 1331 |
| LMArena Russian | 1261 | 1343 |
| LMArena French | — | 1369 |
| LMArena Korean | — | 1282 |
| LMArena Spanish | — | 1389 |
Instruction Following gpt-oss-120b leads
GPT-4.1 nano: 67.8 (#193), gpt-oss-120b: 69.3 (#173)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| IFEval | 84.3% | 83.6% |
| LMArena Instruction Following | 1267 | 1318 |
Long Context gpt-oss-120b leads
GPT-4.1 nano: 23.7 (#296), gpt-oss-120b: 31.4 (#278)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| Fiction.LiveBench | 25% | 44.4% |
| LMArena Longer Query | 1283 | 1319 |
Writing & Preference gpt-oss-120b leads
GPT-4.1 nano: 40.5 (#243), gpt-oss-120b: 46.5 (#217)
| Benchmark | GPT-4.1 nano | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1285 | 1365 |
| LMArena Creative Writing | 1260 | 1275 |
| EQ-Bench Creative Writing | 946 | 961 |
| WildBench | 81.2% | 84.5% |
| LMArena Multi-Turn | 1277 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
Frequently asked questions
Is GPT-4.1 nano better than gpt-oss-120b?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 27.9 on the Noometry Index.
Which is cheaper, GPT-4.1 nano 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; GPT-4.1 nano lists at $0.10 and $0.40.
Is GPT-4.1 nano or gpt-oss-120b better for coding?
gpt-oss-120b scores higher on coding benchmarks: 33.5 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 131K.
How many benchmarks do GPT-4.1 nano and gpt-oss-120b share?
31 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and gpt-oss-120b has 48.