Model comparison
Claude Instant vs phi-3-medium 14B
phi-3-medium 14B has enough public results to be ranked (#306); Claude Instant does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
MicrosoftSummary
- They share 4 benchmarks with published results for both.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Claude Instant | phi-3-medium 14B | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 29.5 | 29.7 |
| Released | 2023-08-09 | 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 Not comparable
Claude Instant: —, phi-3-medium 14B: 36.8 (#201)
| Benchmark | Claude Instant | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
| HumanEval+ | 50.6% | — |
Reasoning Not comparable
Claude Instant: 19.6, phi-3-medium 14B: —
| Benchmark | Claude Instant | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 120.28 | 121.23 |
| DTBench | 45.8% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Not comparable
Claude Instant: —, phi-3-medium 14B: 27.3 (#250)
| Benchmark | Claude Instant | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |
| GSM8K | 86.7% | — |
Knowledge Not comparable
Claude Instant: —, phi-3-medium 14B: 9.1 (#306)
| Benchmark | Claude Instant | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 86.3% | 91.6% |
| MMLU | 73.4% | 78% |
| TriviaQA | 78.9% | 73.9% |
| GPQA Diamond | — | 27.6% |
| OpenBookQA | — | 87.4% |
Frequently asked questions
Is Claude Instant better than phi-3-medium 14B?
phi-3-medium 14B has enough public results to be ranked (#306); Claude Instant does not yet, so treat this comparison as directional.
How many benchmarks do Claude Instant and phi-3-medium 14B share?
4 benchmarks have published results for both models. Claude Instant has 7 scored results on Noometry and phi-3-medium 14B has 13.