# gpt-oss-20b vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-grok-4-20
- Last updated: 2026-10-12
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 19.3.
- The biggest single-benchmark swing is Terminal-Bench: 3.4% for gpt-oss-20b and 57.3% for Grok 4.20 (Non-Reasoning).
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.

## Snapshot

| | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 32.5 | 48.6 |
| Rank | 255 | 54 |
| Context | 131K | 1M |
| Input $/M | $0.018 | $1.25 |
| Output $/M | $0.09 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Grok 4.20 (Non-Reasoning): 42.1 (#112)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 40.9% | 52.3% |
| LMArena Coding | 1306 | 1459 |
| ALE-Bench | 566.05 | 1,150 |
| LMArena WebDev | — | 1375 |
| SciCode | 34.4% | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Grok 4.20 (Non-Reasoning): 34.4 (#46)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 3.4% | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Grok 4.20 (Non-Reasoning): 52.3 (#32)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 75% |
| Chess Puzzles | 4% | 24% |
| LMArena Hard Prompts | 1274 | 1451 |
| DTBench | 68% | 90.1% |
| LMCA | 14.5% | 38.7% |
| Epoch Capabilities Index | 137.82 | 151.98 |
| ARC-AGI-2 | — | 65.1% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 1.4% | — |
| Thematic Generalization | — | 63.8% |
| ForecastBench | — | 61.4 |

## Math

- gpt-oss-20b: 39.4 (#103)
- Grok 4.20 (Non-Reasoning): 48.2 (#65)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 92.2% |
| LMArena Math | 1317 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 56.5% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Grok 4.20 (Non-Reasoning): 52.8 (#60)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 60.8% | 89.3% |
| LMArena Expert | 1258 | 1439 |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |

## Multimodal

- gpt-oss-20b: —
- Grok 4.20 (Non-Reasoning): 33.3 (#98)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Grok 4.20 (Non-Reasoning): 54.5 (#40)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1268 | 1441 |
| LMArena Chinese | 1314 | 1481 |
| LMArena German | 1255 | 1465 |
| LMArena Japanese | 1244 | 1449 |
| LMArena Korean | 1236 | 1417 |
| LMArena Russian | 1278 | 1458 |
| LMArena Spanish | 1267 | 1443 |
| LMArena French | — | 1476 |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Grok 4.20 (Non-Reasoning): 74.8 (#83)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1236 | 1420 |
| IFEval | 73.2% | — |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Grok 4.20 (Non-Reasoning): 45.5 (#34)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1250 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Grok 4.20 (Non-Reasoning): 65.7 (#44)

| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1287 | 1451 |
| LMArena Creative Writing | 1201 | 1438 |
| EQ-Bench Creative Writing | 666 | 1574 |
| LMArena Multi-Turn | 1268 | 1456 |
| WildBench | 73.7% | — |

## FAQ

### Is gpt-oss-20b better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

### Which is cheaper, gpt-oss-20b or Grok 4.20 (Non-Reasoning)?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is gpt-oss-20b or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 37.6 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.

### How many benchmarks do gpt-oss-20b and Grok 4.20 (Non-Reasoning) share?

27 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.