Model comparison
Gemini 3.5 Flash Lite vs Phi 3 Mini 4k Instruct
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MicrosoftSummary
- They share 18 benchmarks with published results for both. Gemini 3.5 Flash Lite scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.5 Flash Lite leads 64.4 to 27.7.
- The biggest single-benchmark swing is Chess Puzzles: 22% for Gemini 3.5 Flash Lite and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 41.8 | 27.4 |
| Released | 2026-07-21 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 38 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 42.1 (#96), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1455 | 1093 |
| LMArena WebDev | 1440 | — |
| SciCode | 41.3% | — |
| WeirdML | 39% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 765.27 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Gemini 3.5 Flash Lite: 28.6 (#82), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| GDP.pdf | 10% | — |
Reasoning Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 27.8 (#95), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 22% | 0% |
| LMArena Hard Prompts | 1441 | 1072 |
| ARC-AGI-2 | 10.3% | — |
| NYT Connections (extended) | 60.4% | — |
| ARC-AGI-1 | 53.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 83.5% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 37.6% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 145.12 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 25.7 (#245), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1431 | 1111 |
| FrontierMath (Tiers 1-3) | 26% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 13% | — |
| LiveBench Math | — | 15.7% |
Knowledge Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 50.0 (#66), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1430 | 1045 |
| GPQA Diamond | 83.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemini 3.5 Flash Lite: 40.3 (#38), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1266 | — |
Multilingual Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 53.8 (#59), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1428 | 1021 |
| LMArena Chinese | 1467 | 1021 |
| LMArena French | 1452 | 1075 |
| LMArena German | 1454 | 1044 |
| LMArena Japanese | 1428 | 935 |
| LMArena Korean | 1406 | 905 |
| LMArena Russian | 1443 | 1022 |
| LMArena Spanish | 1440 | 1084 |
Instruction Following Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 75.0 (#77), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1420 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 43.8 (#80), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1435 | 1044 |
Writing & Preference Gemini 3.5 Flash Lite leads
Gemini 3.5 Flash Lite: 64.4 (#55), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Gemini 3.5 Flash Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1436 | 1073 |
| LMArena Creative Writing | 1419 | 1037 |
| LMArena Multi-Turn | 1445 | 1018 |
| EQ-Bench Creative Writing | 1559 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemini 3.5 Flash Lite better than Phi 3 Mini 4k Instruct?
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.8 to 27.4 on the Noometry Index.
Is Gemini 3.5 Flash Lite or Phi 3 Mini 4k Instruct better for coding?
Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.1 versus 26.1 in the Noometry coding category.
How many benchmarks do Gemini 3.5 Flash Lite and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Gemini 3.5 Flash Lite has 38 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.