# gpt-oss-120b vs Grok 4

> Grok 4 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-oss-120b-vs-grok-4
- Last updated: 2026-10-12
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. gpt-oss-120b scores higher in 1 category and Grok 4 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 31.4.
- The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for gpt-oss-120b and 94.4% for Grok 4.
- gpt-oss-120b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-120b | Grok 4 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 36.3 | 48.1 |
| Rank | 217 | 56 |
| Context | 131K | — |
| Input $/M | $0.037 | — |
| Output $/M | $0.17 | — |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-120b: 33.5 (#256)
- Grok 4: 50.3 (#46)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| Aider Polyglot | 41.8% | 79.6% |
| WeirdML | 48.2% | 45.7% |
| LMArena Coding | 1380 | 1408 |
| SWE-bench Verified (bash only) | 26% | — |
| SciCode | 36% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |

## Agentic & Tool Use

- gpt-oss-120b: 12.2 (#153)
- Grok 4: 32.3 (#68)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| Terminal-Bench | 18.7% | 27.2% |
| METR Time Horizons | 56.6% | 66.6% |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| Vending-Bench 2 | -21.53 | — |

## Reasoning

- gpt-oss-120b: 20.0 (#245)
- Grok 4: 36.7 (#65)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| SimpleBench | 22.1% | 60.5% |
| Kagi LLM Benchmark | 58.6% | 73.6% |
| Chess Puzzles | 20% | 28% |
| LMArena Hard Prompts | 1364 | 1409 |
| Epoch Capabilities Index | 139.93 | 146.44 |
| ARC-AGI-2 | — | 16% |
| ARC-AGI-1 | — | 66.7% |
| CritPt | 1.1% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| ForecastBench | — | 60.9 |

## Math

- gpt-oss-120b: 52.5 (#50)
- Grok 4: 48.4 (#64)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 84% |
| Omni-MATH | 68.8% | 60.3% |
| LMArena Math | 1389 | 1422 |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- gpt-oss-120b: 42.4 (#96)
- Grok 4: 53.8 (#55)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| GPQA Diamond | 75.8% | 87% |
| MMLU-Pro | 79.5% | 85.1% |
| Confabulations | 15.7% | 12.4% |
| GPQA (HELM) | 68.4% | 72.7% |
| LMArena Expert | 1356 | 1415 |
| Vectara Hallucination Rate | 14.2% | — |

## Multimodal

- gpt-oss-120b: —
- Grok 4: 33.7 (#94)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 45% |

## Multilingual

- gpt-oss-120b: 48.0 (#147)
- Grok 4: 51.8 (#103)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| LMArena Non-English | 1351 | 1403 |
| LMArena Chinese | 1385 | 1427 |
| LMArena French | 1369 | 1418 |
| LMArena German | 1353 | 1429 |
| LMArena Japanese | 1331 | 1394 |
| LMArena Korean | 1282 | 1377 |
| LMArena Russian | 1343 | 1410 |
| LMArena Spanish | 1389 | 1420 |

## Instruction Following

- gpt-oss-120b: 69.3 (#173)
- Grok 4: 79.2 (#5)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| IFEval | 83.6% | 94.9% |
| LMArena Instruction Following | 1318 | 1387 |

## Long Context

- gpt-oss-120b: 31.4 (#278)
- Grok 4: 63.1 (#4)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| Fiction.LiveBench | 44.4% | 94.4% |
| LMArena Longer Query | 1319 | 1409 |

## Writing & Preference

- gpt-oss-120b: 46.5 (#217)
- Grok 4: 58.5 (#116)

| Benchmark | gpt-oss-120b | Grok 4 |
|---|---|---|
| LMArena Text | 1365 | 1411 |
| LMArena Creative Writing | 1275 | 1397 |
| Short-Story Creative Writing | 77.1% | 76.9% |
| WildBench | 84.5% | 79.7% |
| LMArena Multi-Turn | 1340 | 1416 |
| EQ-Bench Creative Writing | 961 | — |

## FAQ

### Is gpt-oss-120b better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 36.3 on the Noometry Index.

### Is gpt-oss-120b or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 33.5 in the Noometry coding category.

### How many benchmarks do gpt-oss-120b and Grok 4 share?

35 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok 4 has 48.