Model comparison
gpt-oss-120b vs Grok 4.1
Grok 4.1 is the stronger model overall, scoring 41.5 to 36.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Grok 4.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Grok 4.1 leads 34.1 to 12.2.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Grok 4.1 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 36.3 | 41.5 |
| Released | 2025-08-05 | 2025-11-17 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-120b: 33.5 (#256), Grok 4.1: 33.7 (#253)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Coding | 1380 | 1445 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1214 |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Grok 4.1 leads
gpt-oss-120b: 12.2 (#153), Grok 4.1: 34.1 (#49)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Cybench | — | 39% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Grok 4.1 leads
gpt-oss-120b: 20.0 (#245), Grok 4.1: 29.5 (#91)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1435 |
| 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), Grok 4.1: 38.9 (#120)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Math | 1389 | 1422 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Grok 4.1: 39.5 (#133)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Expert | 1356 | 1417 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual Grok 4.1 leads
gpt-oss-120b: 48.0 (#147), Grok 4.1: 53.4 (#68)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1351 | 1425 |
| LMArena Chinese | 1385 | 1465 |
| LMArena French | 1369 | 1448 |
| LMArena German | 1353 | 1446 |
| LMArena Japanese | 1331 | 1397 |
| LMArena Korean | 1282 | 1407 |
| LMArena Russian | 1343 | 1434 |
| LMArena Spanish | 1389 | 1438 |
Instruction Following Grok 4.1 leads
gpt-oss-120b: 69.3 (#173), Grok 4.1: 73.8 (#111)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1400 |
| IFEval | 83.6% | — |
Long Context Grok 4.1 leads
gpt-oss-120b: 31.4 (#278), Grok 4.1: 43.2 (#100)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1319 | 1416 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Grok 4.1 leads
gpt-oss-120b: 46.5 (#217), Grok 4.1: 62.4 (#75)
| Benchmark | gpt-oss-120b | Grok 4.1 |
|---|---|---|
| LMArena Text | 1365 | 1437 |
| LMArena Creative Writing | 1275 | 1411 |
| LMArena Multi-Turn | 1340 | 1437 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Grok 4.1?
Grok 4.1 is the stronger model overall, scoring 41.5 to 36.3 on the Noometry Index.
Is gpt-oss-120b or Grok 4.1 better for coding?
They score almost the same on coding (33.5 vs 33.7); test both on your own repository before choosing.
How many benchmarks do gpt-oss-120b and Grok 4.1 share?
17 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok 4.1 has 19.