Microsoft, open weights
Phi 3 Small 8k Instruct
Phi 3 Small 8k Instruct by Microsoft ranks 314th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.3. Its strongest category is knowledge, where it ranks 240th.
Last verified
Specifications
- Noometry rank
- #314 of 354
- Index score
- 29.3
- Evidence
- Confirmed 32 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 27.9
- Reasoning 14.8
- Math 27.6
- Knowledge 29.1
- Multilingual 28.5
- Instruction Following 51.9
- Long Context 33.0
- Writing & Preference 31.1
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 27.9 | #318 | 2 |
| Reasoning | 14.8 | #323 | 3 |
| Math | 27.6 | #248 | 2 |
| Knowledge | 29.1 | #240 | 1 |
| Multilingual | 28.5 | #272 | 1 |
| Instruction Following | 51.9 | #292 | 2 |
| Long Context | 33.0 | #267 | 1 |
| Writing & Preference | 31.1 | #284 | 4 |
Strengths and weaknesses
Categories where Phi 3 Small 8k Instruct places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 27.6 | −9.0 | #248 of 327, top 76% |
| Knowledge | 29.1 | −8.3 | #240 of 314, top 77% |
| Long Context | 33.0 | −7.9 | #267 of 296, top 91% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 51.9 | −19.4 | #292 of 305, top 96% |
| Coding | 27.9 | −10.9 | #318 of 340, top 94% |
| Reasoning | 14.8 | −8.8 | #323 of 350, top 93% |
Closest competitors
The models ranked just above and below Phi 3 Small 8k Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Claude 3 Opus | #310 | 29.5 | — | — | Compare |
| DBRX | #311 | 29.4 | — | — | Compare |
| Gemma 2 27B | #312 | 29.4 | $0.65 | — | Compare |
| Gemma 1.1 2b IT | #313 | 29.3 | — | — | Compare |
| Claude 3.5 Haiku | #315 | 29.2 | — | — | Compare |
| GPT-4 | #316 | 29.1 | $37.50 | — | Compare |
| Llama 2-7B | #317 | 29.1 | — | — | Compare |
| Granite 4.0 Micro | #318 | 29.0 | $0.0408 | — | 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 |
|---|---|---|---|---|---|
| LiveBench Coding | 20.3% | #34 of 39, top 88% | Epoch AI | ||
| LMArena Coding | 1101 | #269 of 294, top 92% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 15.9% | #38 of 39, top 98% | Epoch AI | ||
| LMArena Hard Prompts | 1100 | #268 of 297, top 91% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 30.3% | #38 of 39, top 98% | Epoch AI | ||
| Adversarial NLI | 58.1% | #2 of 9, top 23% | Epoch AI | ||
| BIG-Bench Hard | 79.1% | #6 of 27, top 23% | Epoch AI | ||
| HellaSwag | 77% | #21 of 29, top 73% | Epoch AI | ||
| LiveBench | 24% | #37 of 39, top 95% | Epoch AI | ||
| WinoGrande | 81.5% | #13 of 43, top 31% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Math | 17.6% | #37 of 39, top 95% | Epoch AI | ||
| LMArena Math | 1151 | #252 of 285, top 89% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1067 | #257 of 273, top 95% | LMArena | 2026-10-08 | |
| ARC (AI2) Challenge | 90.7% | #6 of 39, top 16% | Epoch AI | ||
| MMLU | 75.7% | #33 of 81, top 41% | Epoch AI | ||
| OpenBookQA | 88% | #2 of 19, top 11% | Epoch AI | ||
| TriviaQA | 58.1% | #23 of 25, top 92% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1058 | #272 of 297, top 92% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1061 | #264 of 285, top 93% | LMArena | 2026-10-08 | |
| LMArena French | 1135 | #209 of 223, top 94% | LMArena | 2026-10-08 | |
| LMArena German | 1080 | #215 of 231, top 94% | LMArena | 2026-10-08 | |
| LMArena Japanese | 966 | #204 of 211, top 97% | LMArena | 2026-10-08 | |
| LMArena Korean | 894 | #211 of 213, top 100% | LMArena | 2026-10-08 | |
| LMArena Russian | 1111 | #255 of 283, top 91% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1111 | #213 of 226, top 95% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 47.2% | #38 of 39, top 98% | Epoch AI | ||
| LMArena Instruction Following | 1087 | #272 of 298, top 92% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1088 | #272 of 291, top 94% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1110 | #270 of 297, top 91% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1083 | #272 of 295, top 93% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1068 | #271 of 295, top 92% | LMArena | 2026-10-08 | |
| LiveBench Language | 12.9% | #37 of 39, top 95% | Epoch AI |
Compare Phi 3 Small 8k Instruct
- Phi 3 Small 8k Instruct vs Gemma 1.1 2b IT
- Phi 3 Small 8k Instruct vs Claude 3.5 Haiku
- Phi 3 Small 8k Instruct vs Gemma 2 27B
- Phi 3 Small 8k Instruct vs GPT-4
- Phi 3 Small 8k Instruct vs DBRX
- Phi 3 Small 8k Instruct vs Llama 2-7B
- Phi 3 Small 8k Instruct vs GPT-6 Astra
- Phi 3 Small 8k Instruct vs Claude Fable 5.1
- Phi 3 Small 8k Instruct vs Gemini 3.8 Flash
- Phi 3 Small 8k Instruct vs Kimi K3
- Phi 3 Small 8k Instruct vs Grok 4.6
- Phi 3 Small 8k Instruct vs Qwen3.8 Max
- Phi 3 Small 8k Instruct vs GLM-5.3
- Phi 3 Small 8k Instruct vs Muse Spark 1.3
Other Microsoft models
Frequently asked questions
How good is Phi 3 Small 8k Instruct?
Phi 3 Small 8k Instruct by Microsoft ranks 314th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.3. Its strongest category is knowledge, where it ranks 240th.
Is Phi 3 Small 8k Instruct open source?
Yes. Phi 3 Small 8k Instruct's weights are downloadable; check the license for commercial terms.
What are Phi 3 Small 8k Instruct's strengths and weaknesses?
Relative to other ranked models, Phi 3 Small 8k Instruct places best in math, knowledge, long context and lowest in instruction following, coding, reasoning.
What is Phi 3 Small 8k Instruct best at?
Its best category is knowledge, where it ranks 240th on Noometry.