Model comparison
Gemini 3.5 Flash vs GPT-4.5
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 36.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 9 categories and GPT-4.5 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.7 to 14.1.
- The biggest single-benchmark swing is ARC-AGI-1: 92.5% for Gemini 3.5 Flash and 10.3% for GPT-4.5.
Side by side
| Gemini 3.5 Flash | GPT-4.5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 54.1 | 36.9 |
| Released | 2026-05-19 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $9 | — |
| Results tracked | 54 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash leads
Gemini 3.5 Flash: 49.1 (#46), GPT-4.5: 41.8 (#102)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| WeirdML | 62.6% | 39.4% |
| LMArena Coding | 1492 | 1397 |
| SWE-bench Verified | 79.3% | — |
| DeepSWE | 37.4% | — |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1499 | — |
| SciCode | 53.1% | — |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 911.02 | — |
Agentic & Tool Use GPT-4.5 leads
Gemini 3.5 Flash: 24.8 (#107), GPT-4.5: 27.6 (#92)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| APEX-Agents | 27.5% | — |
| Cybench | — | 17.5% |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | 5,396 | — |
Reasoning Gemini 3.5 Flash leads
Gemini 3.5 Flash: 62.7 (#16), GPT-4.5: 14.1 (#320)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| ARC-AGI-2 | 72.1% | 0.8% |
| SimpleBench | 76.7% | 34.5% |
| ARC-AGI-1 | 92.5% | 10.3% |
| EnigmaEval | 25.4% | 3.2% |
| LMArena Hard Prompts | 1488 | 1404 |
| Epoch Capabilities Index | 154.55 | 136.74 |
| ForecastBench | 59 | 61.7 |
| NYT Connections (extended) | 92.6% | — |
| CritPt | 13.1% | — |
| Chess Puzzles | 50% | — |
| EBR-Bench | 4.8% | — |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 32% | — |
| DTBench | 94.7% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 47.1% | — |
| Surface Evolver Bench | 58.1% | — |
| LiveBench | — | 69% |
Math Gemini 3.5 Flash leads
Gemini 3.5 Flash: 60.5 (#30), GPT-4.5: 31.0 (#200)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 37.8% |
| LMArena Math | 1502 | 1412 |
| FrontierMath (Tiers 1-3) | 62.8% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.3% | — |
| ProofBench | 31% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Gemini 3.5 Flash leads
Gemini 3.5 Flash: 66.3 (#10), GPT-4.5: 32.4 (#205)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 92.8% | 68.7% |
| LMArena Expert | 1493 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | 66.2% | — |
| Confabulations | — | 13.6% |
Multimodal Gemini 3.5 Flash leads
Gemini 3.5 Flash: 45.7 (#13), GPT-4.5: 37.0 (#68)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1311 | 1195 |
| VPCT | — | 45% |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |
Multilingual Gemini 3.5 Flash leads
Gemini 3.5 Flash: 57.1 (#12), GPT-4.5: 52.7 (#78)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1475 | 1413 |
| LMArena Chinese | 1525 | 1421 |
| LMArena French | 1490 | 1417 |
| LMArena German | 1500 | 1457 |
| LMArena Japanese | 1481 | 1416 |
| LMArena Korean | 1453 | 1392 |
| LMArena Russian | 1491 | 1419 |
| LMArena Spanish | 1478 | — |
Instruction Following Gemini 3.5 Flash leads
Gemini 3.5 Flash: 77.2 (#29), GPT-4.5: 72.8 (#129)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1466 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context Gemini 3.5 Flash leads
Gemini 3.5 Flash: 45.3 (#39), GPT-4.5: 40.4 (#150)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1481 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Gemini 3.5 Flash leads
Gemini 3.5 Flash: 65.5 (#46), GPT-4.5: 57.1 (#129)
| Benchmark | Gemini 3.5 Flash | GPT-4.5 |
|---|---|---|
| LMArena Text | 1481 | 1417 |
| LMArena Creative Writing | 1467 | 1394 |
| LMArena Multi-Turn | 1482 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| EQ-Bench 4 | 1087 | — |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is Gemini 3.5 Flash better than GPT-4.5?
Gemini 3.5 Flash is the stronger model overall, scoring 54.1 to 36.9 on the Noometry Index.
Is Gemini 3.5 Flash or GPT-4.5 better for coding?
Gemini 3.5 Flash scores higher on coding benchmarks: 49.1 versus 41.8 in the Noometry coding category.
How many benchmarks do Gemini 3.5 Flash and GPT-4.5 share?
26 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and GPT-4.5 has 42.