Model comparison
DeepSeek V4.1 Flash vs GPT-4o mini
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 25.5 on the Noometry Index.
Last verified . 26 shared benchmarks.
DeepSeekSummary
- They share 26 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 6.9% for GPT-4o mini.
- Both cost about the same: $0.15 input and $0.60 output per million tokens.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 128K.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | GPT-4o mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 52.8 | 25.5 |
| Released | 2026-09-09 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | 1M | 128K |
| Max output | 393K | 16K |
| Input $ / M tokens | $0.15 | $0.15 |
| Output $ / M tokens | $0.60 | $0.60 |
| Results tracked | 37 | 60 |
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-4o mini: 22.0 (#335)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Coding | 1506 | 1290 |
| Aider Polyglot | — | 3.6% |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 1,092 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), GPT-4o mini: 27.5 (#101)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| APEX-Agents | 39.5% | — |
| BALROG | — | 17.4% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), GPT-4o mini: 8.7 (#347)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1267 |
| Mystery Game Puzzles | 43% | 12% |
| DTBench | 89.9% | 54.4% |
| LMCA | 47% | 10.4% |
| Epoch Capabilities Index | 154.9 | 126.56 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| Surface Evolver Bench | 46.3% | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), GPT-4o mini: 10.4 (#314)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 0.7% |
| OTIS Mock AIME 2024-2025 | 98.3% | 6.9% |
| LMArena Math | 1477 | 1267 |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| GSM8K | — | 91.3% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), GPT-4o mini: 17.7 (#284)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 89.8% | 37.7% |
| LMArena Expert | 1506 | 1235 |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), GPT-4o mini: 25.9 (#122)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1277 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), GPT-4o mini: 42.0 (#199)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1448 | 1266 |
| LMArena Chinese | 1497 | 1265 |
| LMArena French | 1452 | 1297 |
| LMArena German | 1484 | 1272 |
| LMArena Japanese | 1412 | 1216 |
| LMArena Korean | 1452 | 1195 |
| LMArena Russian | 1471 | 1275 |
| LMArena Spanish | 1459 | 1276 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), GPT-4o mini: 61.9 (#239)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1474 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), GPT-4o mini: 39.1 (#186)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1475 | 1289 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), GPT-4o mini: 39.5 (#248)
| Benchmark | DeepSeek V4.1 Flash | GPT-4o mini |
|---|---|---|
| LMArena Text | 1462 | 1286 |
| LMArena Creative Writing | 1435 | 1268 |
| EQ-Bench Creative Writing | 1540 | 873 |
| LMArena Multi-Turn | 1457 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than GPT-4o mini?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 25.5 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.
Is DeepSeek V4.1 Flash or GPT-4o mini better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 128K.
How many benchmarks do DeepSeek V4.1 Flash and GPT-4o mini share?
26 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GPT-4o mini has 60.