Model comparison
GPT-4.1 vs gpt-oss-120b
GPT-4.1 and gpt-oss-120b score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and gpt-oss-120b in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 88.9% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 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 | gpt-oss-120b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.9 | 36.3 |
| Released | 2025-04-14 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 33K | 41K |
| Input $ / M tokens | $2 | $0.037 |
| Output $ / M tokens | $8 | $0.17 |
| Results tracked | 52 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), gpt-oss-120b: 33.5 (#256)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| SWE-bench Verified (bash only) | 39.6% | 26% |
| Aider Polyglot | 52.4% | 41.8% |
| WeirdML | 39% | 48.2% |
| LMArena Coding | 1391 | 1380 |
| ALE-Bench | 558.1 | 575.62 |
| SWE-bench Verified | 48.5% | — |
| SciCode | — | 36% |
| CadEval | 42% | — |
| AlgoTune | — | 1.41 |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), gpt-oss-120b: 12.2 (#153)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| Berkeley Function Calling Leaderboard | 54% | — |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning gpt-oss-120b leads
GPT-4.1: 11.7 (#339), gpt-oss-120b: 20.0 (#245)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| SimpleBench | 27% | 22.1% |
| Kagi LLM Benchmark | 52.3% | 58.6% |
| Chess Puzzles | 6% | 20% |
| LMArena Hard Prompts | 1384 | 1364 |
| DTBench | 68.3% | 76.3% |
| LMCA | 25.6% | 22.1% |
| Epoch Capabilities Index | 136.78 | 139.93 |
| ARC-AGI-2 | 0.4% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 1.1% |
| EnigmaEval | 2.2% | — |
| Mystery Game Puzzles | — | 2% |
| Surface Evolver Bench | — | 25% |
| ForecastBench | 61.5 | — |
Math gpt-oss-120b leads
GPT-4.1: 22.3 (#280), gpt-oss-120b: 52.5 (#50)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 88.9% |
| Omni-MATH | 47.1% | 68.8% |
| LMArena Math | 1370 | 1389 |
| FrontierMath (Tiers 1-3) | 6% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge gpt-oss-120b leads
GPT-4.1: 37.1 (#160), gpt-oss-120b: 42.4 (#96)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 66.9% | 75.8% |
| MMLU-Pro | 81.1% | 79.5% |
| Vectara Hallucination Rate | 5.6% | 14.2% |
| GPQA (HELM) | 65.9% | 68.4% |
| LMArena Expert | 1364 | 1356 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| Confabulations | — | 15.7% |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), gpt-oss-120b: —
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), gpt-oss-120b: 48.0 (#147)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1370 | 1351 |
| LMArena Chinese | 1382 | 1385 |
| LMArena French | 1382 | 1369 |
| LMArena German | 1381 | 1353 |
| LMArena Japanese | 1319 | 1331 |
| LMArena Korean | 1339 | 1282 |
| LMArena Russian | 1377 | 1343 |
| LMArena Spanish | 1376 | 1389 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), gpt-oss-120b: 69.3 (#173)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| IFEval | 83.8% | 83.6% |
| LMArena Instruction Following | 1367 | 1318 |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#163), gpt-oss-120b: 31.4 (#278)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| Fiction.LiveBench | 63.9% | 44.4% |
| LMArena Longer Query | 1385 | 1319 |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), gpt-oss-120b: 46.5 (#217)
| Benchmark | GPT-4.1 | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1383 | 1365 |
| LMArena Creative Writing | 1363 | 1275 |
| EQ-Bench Creative Writing | 1420 | 961 |
| WildBench | 85.4% | 84.5% |
| LMArena Multi-Turn | 1398 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
Frequently asked questions
Is GPT-4.1 better than gpt-oss-120b?
GPT-4.1 and gpt-oss-120b score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4.1 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 lists at $2 and $8.
Is GPT-4.1 or gpt-oss-120b better for coding?
They score almost the same on coding (34.4 vs 33.5); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 131K.
How many benchmarks do GPT-4.1 and gpt-oss-120b share?
37 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and gpt-oss-120b has 48.