Model comparison
Gemini 1.5 Flash (May 2024) vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.2 on the Noometry Index.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 0 categories and Gemini 3 Flash Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Flash Preview leads 58.8 to 26.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.3% for Gemini 1.5 Flash (May 2024) and 95.6% for Gemini 3 Flash Preview.
Side by side
| Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | ||
| Noometry Index | 33.2 | 52.3 |
| Released | 2024-05-14 | 2025-12-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 42 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 34.4 (#236), Gemini 3 Flash Preview: 50.9 (#42)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| WeirdML | 24.9% | 61.6% |
| LMArena Coding | 1261 | 1460 |
| SWE-bench Verified | — | 75.4% |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| GSO | — | 9.8% |
| BigCodeBench Instruct | 43.5% | — |
| BigCodeBench Complete | 55.1% | — |
| ALE-Bench | — | 1,367 |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 26.6 (#102), Gemini 3 Flash Preview: 38.7 (#29)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| BALROG | 14.6% | 48.1% |
| Terminal-Bench | — | 64.3% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| DeepResearch Bench | — | 49.8% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 21.7 (#215), Gemini 3 Flash Preview: 49.2 (#37)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1465 |
| DTBench | 53.8% | 89.1% |
| Epoch Capabilities Index | 129.36 | 151.8 |
| ForecastBench | 53.9 | 58.5 |
| ARC-AGI-2 | — | 33.6% |
| SimpleBench | — | 61.1% |
| NYT Connections (extended) | — | 83.1% |
| ARC-AGI-1 | — | 84.7% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 26% |
| LMCA | — | 43.1% |
| PIQA | 87.5% | — |
Math Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), Gemini 3 Flash Preview: 51.7 (#55)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 95.6% |
| LMArena Math | 1269 | 1473 |
| FrontierMath (Feb 2025 set) | 0% | 35.6% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 15% |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 82.4% | — |
Knowledge Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 26.2 (#260), Gemini 3 Flash Preview: 58.8 (#33)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 47.3% | 89.4% |
| LMArena Expert | 1233 | 1462 |
| SimpleQA Verified | — | 66.8% |
| MMLU-Pro | 67.8% | — |
| Vectara Hallucination Rate | — | 13.5% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
| MMLU | 77.9% | — |
Multimodal Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 36.0 (#81), Gemini 3 Flash Preview: 45.5 (#16)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | 1141 | 1285 |
| GeoBench | 76% | 88% |
| Video-MME | 70.3% | — |
| VPCT | — | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
Multilingual Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), Gemini 3 Flash Preview: 55.7 (#27)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1278 | 1458 |
| LMArena Chinese | 1295 | 1511 |
| LMArena French | 1258 | 1477 |
| LMArena German | 1262 | 1497 |
| LMArena Japanese | 1252 | 1489 |
| LMArena Korean | 1221 | 1443 |
| LMArena Russian | 1288 | 1480 |
| LMArena Spanish | 1243 | 1469 |
Instruction Following Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), Gemini 3 Flash Preview: 75.7 (#56)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1258 | 1437 |
| IFEval | 83.1% | — |
Long Context Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 39.0 (#187), Gemini 3 Flash Preview: 44.4 (#67)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1284 | 1452 |
Writing & Preference Gemini 3 Flash Preview leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), Gemini 3 Flash Preview: 65.5 (#45)
| Benchmark | Gemini 1.5 Flash (May 2024) | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1287 | 1466 |
| LMArena Creative Writing | 1285 | 1457 |
| LMArena Multi-Turn | 1253 | 1471 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 33.2 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Gemini 3 Flash Preview share?
27 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Gemini 3 Flash Preview has 59.