Model comparison
Claude 2.1 vs phi-3-medium 14B
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 25.2 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 27.3 to 10.2.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Claude 2.1 and 27.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | phi-3-medium 14B | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 25.2 | 29.7 |
| Released | 2023-11-21 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Claude 2.1: 26.2 (#327), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Claude 2.1 | phi-3-medium 14B |
|---|---|---|
| WeirdML | 7.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Claude 2.1: 21.4 (#221), phi-3-medium 14B: —
| Benchmark | Claude 2.1 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 119.27 | 121.23 |
| DTBench | 51% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 54.2 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Claude 2.1: 10.2 (#315), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Claude 2.1 | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | — | 17.6% |
Knowledge Claude 2.1 leads
Claude 2.1: 15.4 (#292), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Claude 2.1 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 33% | 27.6% |
| MMLU | 73.5% | 78% |
| ARC (AI2) Challenge | — | 91.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Frequently asked questions
Is Claude 2.1 better than phi-3-medium 14B?
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 25.2 on the Noometry Index.
Is Claude 2.1 or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and phi-3-medium 14B share?
3 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and phi-3-medium 14B has 13.