Model comparison
DeepSeek V4 Pro vs Phi-4 Mini
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.5× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 3 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Pro leads 59.5 to 25.3.
- The biggest single-benchmark swing is SciCode: 51% for DeepSeek V4 Pro and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 128K.
Side by side
| DeepSeek V4 Pro | Phi-4 Mini | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 54.3 | 30.9 |
| Released | 2026-04-24 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 393K | 4K |
| Input $ / M tokens | $0.66 | $0.075 |
| Output $ / M tokens | $1.98 | $0.30 |
| Results tracked | 48 | 3 |
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-4 Mini: 28.1 (#317)
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| SciCode | 51% | 10.8% |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| WeirdML | 66.2% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Phi-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Phi-4 Mini: 22.4 (#195)
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| CritPt | 18% | 0% |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math Not comparable
DeepSeek V4 Pro: 64.8 (#30), Phi-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| 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 | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Phi-4 Mini: 25.3 (#262)
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 8.6% | 23.5% |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| LMArena Expert | 1464 | — |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Phi-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| 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-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Phi-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference Not comparable
DeepSeek V4 Pro: 65.5 (#46), Phi-4 Mini: —
| Benchmark | DeepSeek V4 Pro | Phi-4 Mini |
|---|---|---|
| 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-4 Mini?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.5× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.
Is DeepSeek V4 Pro or Phi-4 Mini better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 128K.
How many benchmarks do DeepSeek V4 Pro and Phi-4 Mini share?
3 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Phi-4 Mini has 3.