Model comparison
Gemini 2.5 Flash vs Phi 3 Medium 4k Instruct
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 2.5 Flash leads 52.3 to 30.6.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 39.3 | 33.0 |
| Released | 2025-04-17 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 54 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
Gemini 2.5 Flash: 35.8 (#220), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1424 | 1130 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.8 (#74), Phi 3 Medium 4k Instruct: —
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Phi 3 Medium 4k Instruct leads
Gemini 2.5 Flash: 18.1 (#286), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1127 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1415 | 1173 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Flash leads
Gemini 2.5 Flash: 36.4 (#168), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1426 | 1108 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), Phi 3 Medium 4k Instruct: —
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1409 | 1094 |
| LMArena Chinese | 1450 | 1108 |
| LMArena French | 1433 | 1110 |
| LMArena German | 1418 | 1101 |
| LMArena Japanese | 1405 | 1042 |
| LMArena Korean | 1385 | 954 |
| LMArena Russian | 1415 | 1145 |
| LMArena Spanish | 1421 | 1095 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1113 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1419 | 1120 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 53.8 (#157), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Gemini 2.5 Flash | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1417 | 1138 |
| LMArena Creative Writing | 1400 | 1107 |
| LMArena Multi-Turn | 1408 | 1088 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Phi 3 Medium 4k Instruct?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 33.0 on the Noometry Index.
Is Gemini 2.5 Flash or Phi 3 Medium 4k Instruct better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Flash and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.