Noometry

Microsoft, open weights

Phi 3 Mini 128k Instruct

Phi 3 Mini 128k Instruct by Microsoft ranks 305th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.7. Its strongest category is math, where it ranks 222nd.

Last verified

Noometry rank
#305 of 354
Index score
29.7
Evidence
Confirmed 19 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.

  1. Coding 28.8
  2. Reasoning 19.6
  3. Math 31.6
  4. Knowledge 26.8
  5. Multilingual 25.2
  6. Instruction Following 51.8
  7. Long Context 30.4
  8. Writing & Preference 27.1
CategoryScoreRankResults
Coding28.8#3123
Reasoning19.6#2561
Math31.6#2221
Knowledge26.8#2541
Multilingual25.2#2851
Instruction Following51.8#2941
Long Context30.4#2891
Writing & Preference27.1#3013

Strengths and weaknesses

Categories where Phi 3 Mini 128k Instruct places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Math31.6−4.9#222 of 327, top 68%
Reasoning19.6−4.0#256 of 350, top 74%
Knowledge26.8−10.5#254 of 314, top 81%

Weakest categories

CategoryScorevs medianRank
Long Context30.4−10.6#289 of 296, top 98%
Writing & Preference27.1−26.6#301 of 312, top 97%
Instruction Following51.8−19.4#294 of 305, top 97%

Closest competitors

The models ranked just above and below Phi 3 Mini 128k Instruct. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Gemini 1.5 Flash 8B#30129.9——Compare
Qwen2.5-VL 72B Instruct#30229.9$4.2043Compare
Mistral#30329.9——Compare
OLMo 2 Furious 13B#30429.7——Compare
phi-3-medium 14B#30629.7——Compare
Gemma 2B#30729.6——Compare
Llama 3.1-70B#30829.6$0.40—Compare
Llama 2-13B#30929.6——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

BenchmarkScorePositionSettingSourceDate
BigCodeBench Instruct29.6%#56 of 64, top 88%BigCodeBench2024-05-21
LMArena Coding1039#284 of 294, top 97%LMArena2026-10-08
BigCodeBench Complete40.6%#51 of 66, top 78%BigCodeBench2024-05-21

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1028#286 of 297, top 97%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1089#268 of 285, top 95%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert984#271 of 273, top 100%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1000#285 of 297, top 96%LMArena2026-10-08
LMArena Chinese1016#274 of 285, top 97%LMArena2026-10-08
LMArena French1039#220 of 223, top 99%LMArena2026-10-08
LMArena German1006#227 of 231, top 99%LMArena2026-10-08
LMArena Japanese899#209 of 211, top 100%LMArena2026-10-08
LMArena Korean856#213 of 213, top 100%LMArena2026-10-08
LMArena Russian1004#275 of 283, top 98%LMArena2026-10-08
LMArena Spanish1059#223 of 226, top 99%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1023#289 of 298, top 97%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query996#289 of 291, top 100%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1050#290 of 297, top 98%LMArena2026-10-08
LMArena Creative Writing1024#287 of 295, top 98%LMArena2026-10-08
LMArena Multi-Turn989#289 of 295, top 98%LMArena2026-10-08

Compare Phi 3 Mini 128k Instruct

Other Microsoft models

Frequently asked questions

How good is Phi 3 Mini 128k Instruct?

Phi 3 Mini 128k Instruct by Microsoft ranks 305th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.7. Its strongest category is math, where it ranks 222nd.

Is Phi 3 Mini 128k Instruct open source?

Yes. Phi 3 Mini 128k Instruct's weights are downloadable; check the license for commercial terms.

What are Phi 3 Mini 128k Instruct's strengths and weaknesses?

Relative to other ranked models, Phi 3 Mini 128k Instruct places best in math, reasoning, knowledge and lowest in long context, writing & preference, instruction following.

What is Phi 3 Mini 128k Instruct best at?

Its best category is math, where it ranks 222nd on Noometry.