Model comparison
DeepSeek V4.1 Flash vs gpt-oss-120b
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 36.0 on the Noometry Index. gpt-oss-120b costs 3.7× less per token, which makes it the better buy when DeepSeek V4.1 Flash's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 6 categories and gpt-oss-120b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 19.5.
- The biggest single-benchmark swing is LMCA: 47% for DeepSeek V4.1 Flash and 22.1% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 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-120b | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 50.3 | 36.0 |
| Released | 2026-09-09 | 2025-08-05 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 393K | 41K |
| Input $ / M tokens | $0.15 | $0.037 |
| Output $ / M tokens | $0.60 | $0.17 |
| Results tracked | 25 | 48 |
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: 52.8 (#29), gpt-oss-120b: 33.2 (#251)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| SciCode | 51.9% | 36% |
| LMArena Coding | 1511 | 1380 |
| ALE-Bench | 1,092 | 575.62 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1620 | — |
| WeirdML | — | 48.2% |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: —, gpt-oss-120b: 12.1 (#145)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 46.2 (#39), gpt-oss-120b: 19.5 (#236)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| CritPt | 14.3% | 1.1% |
| LMArena Hard Prompts | 1485 | 1364 |
| DTBench | 89.9% | 76.3% |
| LMCA | 47% | 22.1% |
| Surface Evolver Bench | 46.3% | 25% |
| Epoch Capabilities Index | 155.01 | 139.94 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| NYT Connections (extended) | 89.6% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 2% |
Math gpt-oss-120b leads
DeepSeek V4.1 Flash: 48.4 (#52), gpt-oss-120b: 50.6 (#43)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1493 | 1388 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | 54% | — |
| Omni-MATH | — | 68.8% |
Knowledge Too close to call
DeepSeek V4.1 Flash: 41.6 (#97), gpt-oss-120b: 42.3 (#89)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Expert | 1505 | 1356 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.5 (#29), gpt-oss-120b: 48.2 (#142)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1452 | 1350 |
| LMArena Chinese | 1506 | 1384 |
| LMArena French | 1448 | 1370 |
| LMArena Russian | 1473 | 1343 |
| LMArena Spanish | 1499 | 1388 |
| LMArena German | — | 1355 |
| LMArena Japanese | — | 1332 |
| LMArena Korean | — | 1283 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.6 (#24), gpt-oss-120b: 69.5 (#168)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1475 | 1318 |
| IFEval | — | 83.6% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#46), gpt-oss-120b: 31.4 (#273)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1476 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.8 (#43), gpt-oss-120b: 46.7 (#213)
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1465 | 1366 |
| LMArena Creative Writing | 1436 | 1274 |
| EQ-Bench Creative Writing | 1540 | 961 |
| LMArena Multi-Turn | 1460 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than gpt-oss-120b?
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 36.0 on the Noometry Index. gpt-oss-120b costs 3.7× 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-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.
Is DeepSeek V4.1 Flash or gpt-oss-120b better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 33.2 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-120b share?
22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and gpt-oss-120b has 48.