Model comparison
Gemini 2.5 Flash-Lite vs Phi 3 Mini 4k Instruct
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemini 2.5 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 2.5 Flash-Lite leads 56.8 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 37.0 | 27.9 |
| Released | 2025-06-17 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 33 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 38.5 (#173), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1373 | 1093 |
| WeirdML | 35.2% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 325.9 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash-Lite: 28.0 (#96), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 22.2 (#205), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1072 |
| Kagi LLM Benchmark | 40.5% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 62.8% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 18.1% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 133.94 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 38.0 (#144), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1373 | 1111 |
| Omni-MATH | 48% | — |
| LiveBench Math | — | 15.7% |
Knowledge Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 32.5 (#210), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1373 | 1045 |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 29.1 (#114), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 49.3 (#134), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1369 | 1021 |
| LMArena Chinese | 1404 | 1021 |
| LMArena French | 1388 | 1076 |
| LMArena German | 1389 | 1044 |
| LMArena Japanese | 1359 | 935 |
| LMArena Korean | 1360 | 905 |
| LMArena Russian | 1373 | 1022 |
| LMArena Spanish | 1396 | 1085 |
Instruction Following Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 70.0 (#168), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1367 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 81% | — |
Long Context Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 33.3 (#262), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1373 | 1044 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 56.8 (#135), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemini 2.5 Flash-Lite | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1379 | 1073 |
| LMArena Creative Writing | 1367 | 1037 |
| LMArena Multi-Turn | 1366 | 1018 |
| WildBench | 81.8% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Phi 3 Mini 4k Instruct?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 27.9 on the Noometry Index.
Is Gemini 2.5 Flash-Lite or Phi 3 Mini 4k Instruct better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash-Lite and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.