# gpt-oss-20b vs Grok 4.7

> Grok 4.7 is the stronger model overall, scoring 46.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 83× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-grok-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Grok 4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.7 leads 70.1 to 35.8.
- The biggest single-benchmark swing is SciCode: 34.4% for gpt-oss-20b and 57.4% for Grok 4.7.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 32.1 | 46.6 |
| Rank | 249 | 56 |
| Context | 131K | 500K |
| Input $/M | $0.018 | $2 |
| Output $/M | $0.09 | $6 |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-20b: 37.1 (#185)
- Grok 4.7: 55.0 (#23)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| SciCode | 34.4% | 57.4% |
| LMArena Coding | 1307 | 1423 |
| CursorBench | — | 46.3% |
| LMArena WebDev | — | 1636 |
| FrontierSWE | — | 29.5% |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.2 (#146)
- Grok 4.7: —

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 18.8 (#251)
- Grok 4.7: 40.1 (#49)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| CritPt | 1.4% | 17.7% |
| LMArena Hard Prompts | 1274 | 1409 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 76.8% |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |

## Math

- gpt-oss-20b: 37.6 (#93)
- Grok 4.7: 41.1 (#73)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Math | 1317 | 1393 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| ProofBench | — | 34% |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#186)
- Grok 4.7: 38.7 (#130)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Expert | 1258 | 1413 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multimodal

- gpt-oss-20b: —
- Grok 4.7: 28.8 (#107)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| Furniture Assembly | — | 20.8% |

## Multilingual

- gpt-oss-20b: 42.4 (#192)
- Grok 4.7: 51.2 (#108)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1269 | 1392 |
| LMArena Chinese | 1311 | 1476 |
| LMArena Russian | 1279 | 1396 |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 62.0 (#235)
- Grok 4.7: 74.3 (#98)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1406 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#203)
- Grok 4.7: 43.2 (#97)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1251 | 1416 |

## Writing & Preference

- gpt-oss-20b: 35.8 (#260)
- Grok 4.7: 70.1 (#23)

| Benchmark | gpt-oss-20b | Grok 4.7 |
|---|---|---|
| LMArena Text | 1288 | 1397 |
| LMArena Creative Writing | 1201 | 1391 |
| EQ-Bench Creative Writing | 666 | 2007 |
| LMArena Multi-Turn | 1268 | 1389 |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 46.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 83× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or Grok 4.7?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Grok 4.7 lists at $2 and $6.

### Is gpt-oss-20b or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 37.1 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 131K.

### How many benchmarks do gpt-oss-20b and Grok 4.7 share?

15 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Grok 4.7 has 21.