Model comparison
DeepSeek-V3.1-Terminus vs gpt-oss-20b
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.1 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.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- 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; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 35.8.
- 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 $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 131K.
Side by side
| DeepSeek-V3.1-Terminus | gpt-oss-20b | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 32.1 |
| Released | 2025-09-22 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 164K | 131K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.30 | $0.018 |
| Output $ / M tokens | $1 | $0.09 |
| Results tracked | 16 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), gpt-oss-20b: 37.1 (#185)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| SciCode | 40.6% | 34.4% |
| LMArena Coding | 1426 | 1307 |
| ALE-Bench | 745.17 | 566.05 |
| WeirdML | — | 40.9% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, gpt-oss-20b: 9.2 (#146)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), gpt-oss-20b: 18.8 (#251)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 53.2% |
| CritPt | 1.7% | 1.4% |
| LMArena Hard Prompts | 1427 | 1274 |
| DTBench | 81.3% | 68% |
| LMCA | 28.6% | 14.5% |
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | — | 137.81 |
Math gpt-oss-20b leads
DeepSeek-V3.1-Terminus: 35.7 (#138), gpt-oss-20b: 37.6 (#93)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1402 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, gpt-oss-20b: 34.6 (#186)
| 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 leads
DeepSeek-V3.1-Terminus: 52.3 (#87), gpt-oss-20b: 42.4 (#192)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1407 | 1269 |
| LMArena Russian | 1434 | 1279 |
| LMArena Chinese | — | 1311 |
| LMArena German | — | 1249 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1239 |
| LMArena Spanish | — | 1267 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), gpt-oss-20b: 62.0 (#235)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1406 | 1236 |
| IFEval | — | 73.2% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), gpt-oss-20b: 37.9 (#203)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1426 | 1251 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), gpt-oss-20b: 35.8 (#260)
| Benchmark | DeepSeek-V3.1-Terminus | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1420 | 1288 |
| LMArena Creative Writing | 1404 | 1201 |
| LMArena Multi-Turn | 1411 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than gpt-oss-20b?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 32.1 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 $0.30 and $1.
Is DeepSeek-V3.1-Terminus or gpt-oss-20b better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 37.1 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.