Phi-3.5-mini-instruct: benchmark scores, price and ranking
Phi-3.5-mini-instruct from microsoft ranks #507 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.5), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- microsoft
- Type
- Open-weight / local model
- Open weights
- Yes
- Cheapest API price
- $0.130 in / $0.520 out per million tokens (via azure_ai, observed 2026-10-13T21:47Z)
- Aggregate rank
- #507 of 743 (score 46.5)
Across the 2 benchmarks where at least ten models are scored, Phi-3.5-mini-instruct is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.130 per million tokens, is lower than that of 76% of the 427 models with a listed price.
Phi-3.5-mini-instruct benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GSM8K | 86.2% | #10 of 17 | HuggingFace GSM8K leaderboard | 2026-10-13 |
| MMLU-Pro | 47.9% | #82 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
About Phi-3.5-mini-instruct
Phi-3.5-mini-instruct is an open-weight model that can run on your own hardware from microsoft. The cheapest API listing we track charges $0.130 per million input tokens and $0.520 per million output tokens, through azure_ai. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where Phi-3.5-mini-instruct stands
On our aggregate score, Phi-3.5-mini-instruct is #507 of 743 ranked models, in the lower half. Its score is 46.5; the scale is centred on 50, so it sits 3.5 points below the typical model. That beats 32% of the ranked field. Among the 4 ranked microsoft models it is #2. The next one up is Phi-3-medium-4k-instruct at 48.8. The next one down is Phi-3-mini-128k-instruct at 46.3.
Phi-3.5-mini-instruct, benchmark by benchmark
Phi-3.5-mini-instruct lands below the middle on GSM8K: 86.2%, #10 of 17, with 53% of the field scoring higher. mimo-v2.5-pro leads at 99.6%; the closest result above is granite-4.1-3b at 86.9%. It covers grade-school math word problems. The board median is 86.9%, so Phi-3.5-mini-instruct is 0.7 points below it. Source: HuggingFace GSM8K leaderboard, captured 2026-10-13.
Phi-3.5-mini-instruct lands below the middle on MMLU-Pro: 47.9%, #82 of 136, with 60% of the field scoring higher. Darwin-180B-RSI leads at 88.1%; the closest result above is glm-4-9b at 47.9%. It covers 57-subject knowledge + reasoning. The board median is 55.3%, so Phi-3.5-mini-instruct is 7.4 points below it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
Strengths and weaknesses
Phi-3.5-mini-instruct has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Phi-3.5-mini-instruct costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on mimo-v2.5 ($0.140) and DeepSeek-R1-Distill-Qwen-32B ($0.150).
Reading these numbers
The 2 scores on this page come from 2 sources: HuggingFace GSM8K leaderboard (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #504 Gemini Robotics-ER 1.6 Preview (46.6)
- #505 DeepSeek-V2 (46.6)
- #506 qwen3.6-plus (46.6)
- #508 grok-3 (46.5)
- #509 Mellum2-12B-A2.5B-Instruct-SFT (46.5)
- #510 Qwen2.5-Coder-3B-Instruct (46.5)
More from microsoft
- Phi-3-medium-4k-instruct (#321, 48.8)
- Phi-3-mini-128k-instruct (#527, 46.3)
- Phi-4-mini-instruct (#721, 41.8)
Compare it on the live leaderboard → · How the aggregate score works