Microsoft, open weights
phi-3-medium 14B
phi-3-medium 14B by Microsoft ranks 306th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.7. Its strongest category is coding, where it ranks 201st.
Last verified
Specifications
- Noometry rank
- #306 of 354
- Index score
- 29.7
- Evidence
- Reported 13 results
- Provider
Microsoft- Released
- April 23, 2024
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- —
- Max output
- —
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
Category scores
Each category score combines every public result we have in that category.
- Coding 36.8
- Math 27.3
- Knowledge 9.1
Strengths and weaknesses
Categories where phi-3-medium 14B places highest and lowest among the models ranked in each, with its score against that category's median.
Closest competitors
The models ranked just above and below phi-3-medium 14B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Qwen2.5-VL 72B Instruct | #302 | 29.9 | $4.20 | 43 | Compare |
| Mistral | #303 | 29.9 | — | — | Compare |
| OLMo 2 Furious 13B | #304 | 29.7 | — | — | Compare |
| Phi 3 Mini 128k Instruct | #305 | 29.7 | — | — | Compare |
| Gemma 2B | #307 | 29.6 | — | — | Compare |
| Llama 3.1-70B | #308 | 29.6 | $0.40 | — | Compare |
| Llama 2-13B | #309 | 29.6 | — | — | Compare |
| Claude 3 Opus | #310 | 29.5 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| BigCodeBench Instruct | 37.6% | #40 of 64, top 63% | BigCodeBench | 2024-05-21 | |
| BigCodeBench Complete | 48.7% | #37 of 66, top 57% | BigCodeBench | 2024-05-21 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Adversarial NLI | 55.8% | #4 of 9, top 45% | Epoch AI | ||
| BIG-Bench Hard | 81.4% | #4 of 27, top 15% | Epoch AI | ||
| Epoch Capabilities Index | 121.23 | #165 of 213, top 78% | Epoch AI | 2024-04-23 | |
| HellaSwag | 82.4% | #14 of 29, top 49% | Epoch AI | ||
| WinoGrande | 81.5% | #12 of 43, top 28% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| MATH Level 5 | 17.6% | #65 of 79, top 83% | Epoch AI | 2025-01-31 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 27.6% | #174 of 186, top 94% | Epoch AI | 2025-01-31 | |
| ARC (AI2) Challenge | 91.6% | #5 of 39, top 13% | Epoch AI | ||
| MMLU | 78% | #25 of 81, top 31% | Epoch AI | ||
| OpenBookQA | 87.4% | #3 of 19, top 16% | Epoch AI | ||
| TriviaQA | 73.9% | #16 of 25, top 64% | Epoch AI |
Compare phi-3-medium 14B
- phi-3-medium 14B vs Phi 3 Mini 128k Instruct
- phi-3-medium 14B vs Gemma 2B
- phi-3-medium 14B vs OLMo 2 Furious 13B
- phi-3-medium 14B vs Llama 3.1-70B
- phi-3-medium 14B vs Mistral
- phi-3-medium 14B vs Llama 2-13B
- phi-3-medium 14B vs GPT-6 Astra
- phi-3-medium 14B vs Claude Fable 5.1
- phi-3-medium 14B vs Gemini 3.8 Flash
- phi-3-medium 14B vs Kimi K3
- phi-3-medium 14B vs Grok 4.6
- phi-3-medium 14B vs Qwen3.8 Max
- phi-3-medium 14B vs GLM-5.3
- phi-3-medium 14B vs Muse Spark 1.3
Other Microsoft models
Frequently asked questions
How good is phi-3-medium 14B?
phi-3-medium 14B by Microsoft ranks 306th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.7. Its strongest category is coding, where it ranks 201st.
Is phi-3-medium 14B open source?
Yes. phi-3-medium 14B's weights are downloadable; check the license for commercial terms.
What are phi-3-medium 14B's strengths and weaknesses?
Relative to other ranked models, phi-3-medium 14B places best in coding and lowest in knowledge.
What is phi-3-medium 14B best at?
Its best category is coding, where it ranks 201st on Noometry.