# DeepSeek-V3.1-Terminus vs gpt-oss-20b

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 13× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-gpt-oss-20b
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and gpt-oss-20b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 35.5.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 14.5% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 131K.

## Snapshot

| | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 32.5 |
| Rank | 97 | 255 |
| Context | 164K | 131K |
| Input $/M | $0.27 | $0.018 |
| Output $/M | $1 | $0.09 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- gpt-oss-20b: 37.6 (#192)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| SciCode | 40.6% | 34.4% |
| LMArena Coding | 1426 | 1306 |
| ALE-Bench | 745.17 | 566.05 |
| WeirdML | — | 40.9% |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- gpt-oss-20b: 9.3 (#154)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- gpt-oss-20b: 19.3 (#261)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 53.2% |
| CritPt | 1.7% | 1.4% |
| LMArena Hard Prompts | 1426 | 1274 |
| DTBench | 81.3% | 68% |
| LMCA | 28.6% | 14.5% |
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | — | 137.82 |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- gpt-oss-20b: 39.4 (#103)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1402 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- gpt-oss-20b: 34.6 (#195)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- gpt-oss-20b: 42.2 (#197)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1407 | 1268 |
| LMArena Russian | 1436 | 1278 |
| LMArena Chinese | — | 1314 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Spanish | — | 1267 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- gpt-oss-20b: 61.8 (#240)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1404 | 1236 |
| IFEval | — | 73.2% |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- gpt-oss-20b: 37.9 (#209)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1421 | 1250 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- gpt-oss-20b: 35.5 (#265)

| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1419 | 1287 |
| LMArena Creative Writing | 1403 | 1201 |
| LMArena Multi-Turn | 1411 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |

## FAQ

### Is DeepSeek-V3.1-Terminus better than gpt-oss-20b?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 32.5 on the Noometry Index. gpt-oss-20b costs 13× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1-Terminus or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.27 and $1.

### Is DeepSeek-V3.1-Terminus or gpt-oss-20b better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 37.6 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 131K.

### How many benchmarks do DeepSeek-V3.1-Terminus and gpt-oss-20b share?

16 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and gpt-oss-20b has 34.