Model comparison
DeepSeek V4.1 Flash vs gpt-oss-20b
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 7.3× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
DeepSeekSummary
- They share 25 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and gpt-oss-20b in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 65.3% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 131K.
Side by side
| DeepSeek V4.1 Flash | gpt-oss-20b | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 52.8 | 32.5 |
| Released | 2026-09-09 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 393K | 16K |
| Input $ / M tokens | $0.15 | $0.018 |
| Output $ / M tokens | $0.60 | $0.09 |
| Results tracked | 37 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), gpt-oss-20b: 37.6 (#192)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| SciCode | 51.9% | 34.4% |
| LMArena Coding | 1506 | 1306 |
| ALE-Bench | 1,092 | 566.05 |
| LMArena WebDev | 1619 | — |
| WeirdML | — | 40.9% |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), gpt-oss-20b: 9.3 (#154)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), gpt-oss-20b: 19.3 (#261)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| CritPt | 14.3% | 1.4% |
| LMArena Hard Prompts | 1483 | 1274 |
| DTBench | 89.9% | 68% |
| LMCA | 47% | 14.5% |
| Epoch Capabilities Index | 154.9 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |
| NYT Connections (extended) | 89.6% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 46.3% | — |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), gpt-oss-20b: 39.4 (#103)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 65.3% |
| LMArena Math | 1477 | 1317 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 56.5% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), gpt-oss-20b: 34.6 (#195)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 89.8% | 60.8% |
| LMArena Expert | 1506 | 1258 |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), gpt-oss-20b: —
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), gpt-oss-20b: 42.2 (#197)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1448 | 1268 |
| LMArena Chinese | 1497 | 1314 |
| LMArena German | 1484 | 1255 |
| LMArena Japanese | 1412 | 1244 |
| LMArena Korean | 1452 | 1236 |
| LMArena Russian | 1471 | 1278 |
| LMArena Spanish | 1459 | 1267 |
| LMArena French | 1452 | — |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), gpt-oss-20b: 61.8 (#240)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1474 | 1236 |
| IFEval | — | 73.2% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), gpt-oss-20b: 37.9 (#209)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1475 | 1250 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), gpt-oss-20b: 35.5 (#265)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1462 | 1287 |
| LMArena Creative Writing | 1435 | 1201 |
| EQ-Bench Creative Writing | 1540 | 666 |
| LMArena Multi-Turn | 1457 | 1268 |
| WildBench | — | 73.7% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than gpt-oss-20b?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 7.3× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4.1 Flash 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 V4.1 Flash lists at $0.15 and $0.60.
Is DeepSeek V4.1 Flash or gpt-oss-20b better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 131K.
How many benchmarks do DeepSeek V4.1 Flash and gpt-oss-20b share?
25 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and gpt-oss-20b has 34.