Model comparison
DeepSeek V4 Pro vs phi-3-medium 14B
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 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 Pro 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 Pro leads 59.5 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 91.7% for DeepSeek V4 Pro and 27.6% for phi-3-medium 14B.
Side by side
| DeepSeek V4 Pro | phi-3-medium 14B | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 54.3 | 29.7 |
| Released | 2026-04-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), phi-3-medium 14B: 36.8 (#201)
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1470 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning Not comparable
DeepSeek V4 Pro: 56.5 (#24), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 155.31 | 121.23 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 56.1 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), phi-3-medium 14B: 27.3 (#250)
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| LMArena Math | 1455 | — |
| MATH Level 5 | — | 17.6% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), phi-3-medium 14B: 9.1 (#306)
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 91.7% | 27.6% |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following Not comparable
DeepSeek V4 Pro: 76.1 (#47), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference Not comparable
DeepSeek V4 Pro: 65.5 (#46), phi-3-medium 14B: —
| Benchmark | DeepSeek V4 Pro | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than phi-3-medium 14B?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 29.7 on the Noometry Index.
Is DeepSeek V4 Pro or phi-3-medium 14B better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 36.8 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and phi-3-medium 14B share?
2 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and phi-3-medium 14B has 13.