Microsoft, open weights
Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct by Microsoft ranks 250th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.0. Its strongest category is math, where it ranks 202nd.
Last verified
Specifications
- Noometry rank
- #250 of 354
- Index score
- 33.0
- Evidence
- Confirmed 17 results
- Provider
Microsoft- Released
- Unknown
- 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 32.9
- Reasoning 21.7
- Math 33.4
- Knowledge 30.2
- Multilingual 30.6
- Instruction Following 57.6
- Long Context 34.0
- Writing & Preference 34.1
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 32.9 | #268 | 1 |
| Reasoning | 21.7 | #214 | 1 |
| Math | 33.4 | #202 | 1 |
| Knowledge | 30.2 | #229 | 1 |
| Multilingual | 30.6 | #263 | 1 |
| Instruction Following | 57.6 | #268 | 1 |
| Long Context | 34.0 | #255 | 1 |
| Writing & Preference | 34.1 | #272 | 3 |
Strengths and weaknesses
Categories where Phi 3 Medium 4k Instruct places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multilingual | 30.6 | −16.8 | #263 of 297, top 89% |
| Instruction Following | 57.6 | −13.7 | #268 of 305, top 88% |
| Writing & Preference | 34.1 | −19.6 | #272 of 312, top 88% |
Closest competitors
The models ranked just above and below Phi 3 Medium 4k Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 1.5 Flash (May 2024) | #246 | 33.2 | — | — | Compare |
| Granite 3.1 2b Instruct | #247 | 33.2 | — | — | Compare |
| Gemma 2 2b IT | #248 | 33.1 | — | — | Compare |
| Wizardlm 70b | #249 | 33.0 | — | — | Compare |
| Tulu 3 (Tülu 3) 70B | #251 | 33.0 | — | — | Compare |
| DeepSeek-R1-Distill-Qwen-14B | #252 | 32.7 | — | — | Compare |
| Qwen1.5-14B | #253 | 32.7 | — | — | Compare |
| Olmo 2 0325 32b Instruct | #254 | 32.7 | — | — | 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 |
|---|---|---|---|---|---|
| LMArena Coding | 1130 | #262 of 294, top 90% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1127 | #260 of 297, top 88% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1173 | #243 of 285, top 86% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1108 | #249 of 273, top 92% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1094 | #263 of 297, top 89% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1108 | #257 of 285, top 91% | LMArena | 2026-10-08 | |
| LMArena French | 1110 | #212 of 223, top 96% | LMArena | 2026-10-08 | |
| LMArena German | 1101 | #211 of 231, top 92% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1042 | #192 of 211, top 91% | LMArena | 2026-10-08 | |
| LMArena Korean | 954 | #207 of 213, top 98% | LMArena | 2026-10-08 | |
| LMArena Russian | 1145 | #251 of 283, top 89% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1095 | #216 of 226, top 96% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1113 | #264 of 298, top 89% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1120 | #263 of 291, top 91% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1138 | #260 of 297, top 88% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1107 | #263 of 295, top 90% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1088 | #269 of 295, top 92% | LMArena | 2026-10-08 |
Compare Phi 3 Medium 4k Instruct
- Phi 3 Medium 4k Instruct vs Wizardlm 70b
- Phi 3 Medium 4k Instruct vs Tulu 3 (Tülu 3) 70B
- Phi 3 Medium 4k Instruct vs Gemma 2 2b IT
- Phi 3 Medium 4k Instruct vs DeepSeek-R1-Distill-Qwen-14B
- Phi 3 Medium 4k Instruct vs Granite 3.1 2b Instruct
- Phi 3 Medium 4k Instruct vs Qwen1.5-14B
- Phi 3 Medium 4k Instruct vs GPT-6 Astra
- Phi 3 Medium 4k Instruct vs Claude Fable 5.1
- Phi 3 Medium 4k Instruct vs Gemini 3.8 Flash
- Phi 3 Medium 4k Instruct vs Kimi K3
- Phi 3 Medium 4k Instruct vs Grok 4.6
- Phi 3 Medium 4k Instruct vs Qwen3.8 Max
- Phi 3 Medium 4k Instruct vs GLM-5.3
- Phi 3 Medium 4k Instruct vs Muse Spark 1.3
Other Microsoft models
Frequently asked questions
How good is Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct by Microsoft ranks 250th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.0. Its strongest category is math, where it ranks 202nd.
Is Phi 3 Medium 4k Instruct open source?
Yes. Phi 3 Medium 4k Instruct's weights are downloadable; check the license for commercial terms.
What are Phi 3 Medium 4k Instruct's strengths and weaknesses?
Relative to other ranked models, Phi 3 Medium 4k Instruct places best in reasoning, math, knowledge and lowest in multilingual, instruction following, writing & preference.
What is Phi 3 Medium 4k Instruct best at?
Its best category is math, where it ranks 202nd on Noometry.