Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs phi-3-medium 14B
phi-3-medium 14B has enough public results to be ranked (#306); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 9 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 9 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and phi-3-medium 14B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 36.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.9% for DeepSeek-V2 (MoE-236B, May 2024) and 37.6% for phi-3-medium 14B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | phi-3-medium 14B | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 40.3 | 29.7 |
| Released | 2024-05-07 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), phi-3-medium 14B: 36.8 (#201)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 37.6% |
| BigCodeBench Complete | 59.4% | 48.7% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, phi-3-medium 14B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | phi-3-medium 14B |
|---|---|---|
| BIG-Bench Hard | 78.8% | 81.4% |
| Epoch Capabilities Index | 124.77 | 121.23 |
| HellaSwag | 87.1% | 82.4% |
| WinoGrande | 86.3% | 81.5% |
| Adversarial NLI | — | 55.8% |
| PIQA | 83.9% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, phi-3-medium 14B: 27.3 (#250)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, phi-3-medium 14B: 9.1 (#306)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 91.6% |
| MMLU | 78.4% | 78% |
| TriviaQA | 80% | 73.9% |
| GPQA Diamond | — | 27.6% |
| OpenBookQA | — | 87.4% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than phi-3-medium 14B?
phi-3-medium 14B has enough public results to be ranked (#306); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or phi-3-medium 14B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 36.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and phi-3-medium 14B share?
9 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and phi-3-medium 14B has 13.