Model comparison
Gemini 3.6 Flash vs Phi 3 Mini 4k Instruct
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MicrosoftSummary
- They share 18 benchmarks with published results for both. Gemini 3.6 Flash 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 reasoning, where Gemini 3.6 Flash leads 58.8 to 14.1.
- The biggest single-benchmark swing is Chess Puzzles: 43% for Gemini 3.6 Flash 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 3.6 Flash | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 54.1 | 27.9 |
| Released | 2026-07-21 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $3.75 | — |
| Results tracked | 46 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Gemini 3.6 Flash: 50.0 (#48), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1491 | 1093 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1538 | — |
| SciCode | 52.7% | — |
| WeirdML | 56.1% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 715.52 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Gemini 3.6 Flash: 32.3 (#65), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |
Reasoning Gemini 3.6 Flash leads
Gemini 3.6 Flash: 58.8 (#22), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 43% | 0% |
| LMArena Hard Prompts | 1485 | 1072 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 89% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 30% | — |
| DTBench | 95.5% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 44.9% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 154.25 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Gemini 3.6 Flash leads
Gemini 3.6 Flash: 57.3 (#40), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1505 | 1111 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |
| OTIS Mock AIME 2024-2025 | 94.2% | — |
| ProofBench | 36% | — |
| LiveBench Math | — | 15.7% |
Knowledge Gemini 3.6 Flash leads
Gemini 3.6 Flash: 67.8 (#8), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1488 | 1045 |
| GPQA Diamond | 94.1% | — |
| SimpleQA Verified | 66.2% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemini 3.6 Flash: 38.5 (#64), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1298 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |
Multilingual Gemini 3.6 Flash leads
Gemini 3.6 Flash: 56.5 (#19), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1469 | 1021 |
| LMArena Chinese | 1531 | 1021 |
| LMArena French | 1504 | 1076 |
| LMArena German | 1478 | 1044 |
| LMArena Japanese | 1476 | 935 |
| LMArena Korean | 1431 | 905 |
| LMArena Russian | 1487 | 1022 |
| LMArena Spanish | 1475 | 1085 |
Instruction Following Gemini 3.6 Flash leads
Gemini 3.6 Flash: 77.0 (#33), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1466 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Gemini 3.6 Flash leads
Gemini 3.6 Flash: 45.1 (#50), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1474 | 1044 |
Writing & Preference Gemini 3.6 Flash leads
Gemini 3.6 Flash: 68.2 (#27), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemini 3.6 Flash | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1479 | 1073 |
| LMArena Creative Writing | 1465 | 1037 |
| LMArena Multi-Turn | 1481 | 1018 |
| EQ-Bench Creative Writing | 1604 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemini 3.6 Flash better than Phi 3 Mini 4k Instruct?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 27.9 on the Noometry Index.
Is Gemini 3.6 Flash or Phi 3 Mini 4k Instruct better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemini 3.6 Flash and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.