Model comparison
DeepSeek V4 Flash vs phi-3-medium 14B
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 2 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Flash leads 55.4 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 91% for DeepSeek V4 Flash and 27.6% for phi-3-medium 14B.
Side by side
| DeepSeek V4 Flash | phi-3-medium 14B | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 53.6 | 29.7 |
| Released | 2026-04-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), phi-3-medium 14B: 36.8 (#201)
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1457 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 1,306 | — |
Reasoning Not comparable
DeepSeek V4 Flash: 53.7 (#30), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 154.49 | 121.23 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| LMArena Hard Prompts | 1444 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), phi-3-medium 14B: 27.3 (#250)
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| LMArena Math | 1427 | — |
| MATH Level 5 | — | 17.6% |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), phi-3-medium 14B: 9.1 (#306)
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 91% | 27.6% |
| SimpleQA Verified | 33.6% | — |
| LMArena Expert | 1441 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
DeepSeek V4 Flash: 53.0 (#72), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1468 | — |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Not comparable
DeepSeek V4 Flash: 74.9 (#81), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1421 | — |
Long Context Not comparable
DeepSeek V4 Flash: 43.8 (#85), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Not comparable
DeepSeek V4 Flash: 63.8 (#61), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Flash | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1432 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | 1559 | — |
| LMArena Multi-Turn | 1449 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than phi-3-medium 14B?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 29.7 on the Noometry Index.
Is DeepSeek V4 Flash or phi-3-medium 14B better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 36.8 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and phi-3-medium 14B share?
2 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and phi-3-medium 14B has 13.