Model comparison
DeepSeek V4.1 Flash vs Llama 3.1-405B
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.7 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
MetaSummary
- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 9.7% for Llama 3.1-405B.
Side by side
| DeepSeek V4.1 Flash | Llama 3.1-405B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 52.8 | 30.7 |
| Released | 2026-09-09 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 42 |
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), Llama 3.1-405B: 33.1 (#262)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1506 | 1291 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 21.4% |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), Llama 3.1-405B: 21.0 (#140)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| APEX-Agents | 39.5% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Llama 3.1-405B: 16.8 (#300)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1269 |
| DTBench | 89.9% | 61.4% |
| Epoch Capabilities Index | 154.9 | 128.75 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Llama 3.1-405B: 18.4 (#290)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 9.7% |
| LMArena Math | 1477 | 1281 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Llama 3.1-405B: 30.4 (#227)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 89.8% | 50.9% |
| LMArena Expert | 1506 | 1243 |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), Llama 3.1-405B: —
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Llama 3.1-405B: 40.7 (#214)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1448 | 1248 |
| LMArena Chinese | 1497 | 1242 |
| LMArena French | 1452 | 1279 |
| LMArena German | 1484 | 1252 |
| LMArena Japanese | 1412 | 1208 |
| LMArena Korean | 1452 | 1184 |
| LMArena Russian | 1471 | 1265 |
| LMArena Spanish | 1459 | 1260 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Llama 3.1-405B: 65.9 (#214)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1474 | 1259 |
| IFEval | — | 81.1% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Llama 3.1-405B: 38.4 (#197)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1475 | 1266 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Llama 3.1-405B: 38.9 (#251)
| Benchmark | DeepSeek V4.1 Flash | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1462 | 1284 |
| LMArena Creative Writing | 1435 | 1262 |
| EQ-Bench Creative Writing | 1540 | 870 |
| LMArena Multi-Turn | 1457 | 1297 |
| WildBench | — | 78.3% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Llama 3.1-405B?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.7 on the Noometry Index.
Is DeepSeek V4.1 Flash or Llama 3.1-405B better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 33.1 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Llama 3.1-405B share?
22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Llama 3.1-405B has 42.