Model comparison
DeepSeek V4.1 Flash vs Phi 3 Small 8k Instruct
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 17 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 27.6.
Side by side
| DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 52.8 | 29.3 |
| Released | 2026-09-09 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 32 |
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), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1506 | 1101 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: 31.2 (#69), Phi 3 Small 8k Instruct: —
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1100 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 154.9 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1477 | 1151 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
| LiveBench Math | — | 17.6% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1506 | 1067 |
| GPQA Diamond | 89.8% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), Phi 3 Small 8k Instruct: —
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1448 | 1058 |
| LMArena Chinese | 1497 | 1061 |
| LMArena French | 1452 | 1135 |
| LMArena German | 1484 | 1080 |
| LMArena Japanese | 1412 | 966 |
| LMArena Korean | 1452 | 894 |
| LMArena Russian | 1471 | 1111 |
| LMArena Spanish | 1459 | 1111 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1474 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1475 | 1088 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | DeepSeek V4.1 Flash | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1462 | 1110 |
| LMArena Creative Writing | 1435 | 1083 |
| LMArena Multi-Turn | 1457 | 1068 |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Phi 3 Small 8k Instruct?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.3 on the Noometry Index.
Is DeepSeek V4.1 Flash or Phi 3 Small 8k Instruct better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 27.9 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Phi 3 Small 8k Instruct has 32.