Model comparison
Claude 2 vs Phi-4 Mini
Phi-4 Mini is the stronger model overall, scoring 30.9 to 25.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Phi-4 Mini leads 25.3 to 16.9.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Phi-4 Mini | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 25.0 | 30.9 |
| Released | 2023-07-11 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 8 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Phi-4 Mini: 28.1 (#317)
| Benchmark | Claude 2 | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| HumanEval+ | 61.6% | — |
Reasoning Too close to call
Claude 2: 21.7 (#216), Phi-4 Mini: 22.4 (#195)
| Benchmark | Claude 2 | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.13 | — |
Math Not comparable
Claude 2: 9.3 (#320), Phi-4 Mini: —
| Benchmark | Claude 2 | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 11.7% | — |
Knowledge Phi-4 Mini leads
Claude 2: 16.9 (#287), Phi-4 Mini: 25.3 (#262)
| Benchmark | Claude 2 | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| Vectara Hallucination Rate | — | 23.5% |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Frequently asked questions
Is Claude 2 better than Phi-4 Mini?
Phi-4 Mini is the stronger model overall, scoring 30.9 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Phi-4 Mini share?
0 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Phi-4 Mini has 3.