Model comparison
Gemini 2.0 Flash (Feb 2025) vs Phi 3 Mini 4k Instruct
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 27.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MicrosoftSummary
- They share 25 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) 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 instruction following, where Gemini 2.0 Flash (Feb 2025) leads 74.4 to 47.7.
- The biggest single-benchmark swing is LiveBench Math: 75.8% for Gemini 2.0 Flash (Feb 2025) and 15.7% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 35.1 | 27.9 |
| Released | 2024-12-06 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 63.4% | 15.5% |
| LMArena Coding | 1350 | 1093 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 78.2% | 26.8% |
| LMArena Hard Prompts | 1346 | 1072 |
| LiveBench Data Analysis | 69.4% | 34.7% |
| LiveBench | 66.9% | 22.4% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 1.1% | — |
| DTBench | 63.2% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 135.36 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 75.8% | 15.7% |
| LMArena Math | 1352 | 1111 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1339 | 1045 |
| MMLU | 79.7% | 68.8% |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1342 | 1021 |
| LMArena Chinese | 1373 | 1021 |
| LMArena French | 1391 | 1076 |
| LMArena German | 1353 | 1044 |
| LMArena Japanese | 1294 | 935 |
| LMArena Korean | 1313 | 905 |
| LMArena Russian | 1351 | 1022 |
| LMArena Spanish | 1363 | 1085 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 39.1% |
| LMArena Instruction Following | 1336 | 1053 |
| IFEval | 84.1% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1344 | 1044 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1354 | 1073 |
| LMArena Creative Writing | 1340 | 1037 |
| LMArena Multi-Turn | 1350 | 1018 |
| LiveBench Language | 51.3% | 9.2% |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Phi 3 Mini 4k Instruct?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 27.9 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Phi 3 Mini 4k Instruct better for coding?
Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.