Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-4o
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 28.6 on the Noometry Index.
Last verified . 52 shared benchmarks.
GoogleSummary
- They share 52 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 8 categories and GPT-4o in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 37.9 to 10.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Gemini 2.0 Flash (Feb 2025) and 6.4% for GPT-4o.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-4o | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 28.6 |
| Released | 2024-12-06 | 2024-05-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 54 | 72 |
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), GPT-4o: 24.8 (#328)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 21.6% |
| Aider Polyglot | 38.2% | 45.3% |
| WeirdML | 25.8% | 25.1% |
| BigCodeBench Instruct | 45.9% | 51.1% |
| LiveBench Coding | 63.4% | 51.4% |
| LMArena Coding | 1350 | 1297 |
| BigCodeBench Complete | 59.9% | 61.1% |
| CadEval | 30% | 26% |
| SWE-bench Verified | — | 31% |
| GSO | — | 0% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-4o: 21.0 (#141)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| TheAgentCompany | 11.4% | 8.6% |
| GDPval | — | 9.9% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-4o: 9.4 (#343)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| ARC-AGI-2 | 1.3% | 0% |
| SimpleBench | 31.1% | 17.8% |
| EnigmaEval | 1.1% | 0.8% |
| LiveBench Reasoning | 78.2% | 55.8% |
| LMArena Hard Prompts | 1346 | 1281 |
| DTBench | 63.2% | 64.5% |
| LiveBench Data Analysis | 69.4% | 60.9% |
| Epoch Capabilities Index | 135.36 | 128.97 |
| LiveBench | 66.9% | 55.3% |
| Kagi LLM Benchmark | 37.8% | — |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| LMCA | — | 16.6% |
| ForecastBench | — | 57.7 |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-4o: 10.6 (#312)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 6.4% |
| Omni-MATH | 45.9% | 29.3% |
| LiveBench Math | 75.8% | 49.5% |
| LMArena Math | 1352 | 1285 |
| MATH Level 5 | 82.2% | 53.3% |
| FrontierMath (Feb 2025 set) | 1.7% | 0.3% |
| FrontierMath (Tiers 1-3) | — | 0.4% |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-4o: 28.8 (#242)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| GPQA Diamond | 64.1% | 49.2% |
| Humanity's Last Exam | 6.6% | 2.7% |
| MMLU-Pro | 73.7% | 71.3% |
| Confabulations | 12.4% | 15.3% |
| GPQA (HELM) | 55.6% | 52% |
| LMArena Expert | 1339 | 1250 |
| MMLU | 79.7% | 88.1% |
| SimpleQA Verified | — | 26% |
| Vectara Hallucination Rate | — | 9.6% |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-4o: 34.5 (#91)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| LMArena Vision | 1158 | 1137 |
| GeoBench | 77% | 71% |
| Video-MME | — | 71.9% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-4o: 43.2 (#186)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| LMArena Non-English | 1342 | 1283 |
| LMArena Chinese | 1373 | 1277 |
| LMArena French | 1391 | 1304 |
| LMArena German | 1353 | 1282 |
| LMArena Japanese | 1294 | 1257 |
| LMArena Korean | 1313 | 1234 |
| LMArena Russian | 1351 | 1286 |
| LMArena Spanish | 1363 | 1292 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-4o: 66.6 (#207)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 68.6% |
| IFEval | 84.1% | 81.7% |
| LMArena Instruction Following | 1336 | 1278 |
Long Context GPT-4o leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-4o: 39.4 (#179)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| Fiction.LiveBench | 61.1% | 66.7% |
| LMArena Longer Query | 1344 | 1289 |
Writing & Preference GPT-4o leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-4o: 52.6 (#166)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-4o |
|---|---|---|
| LMArena Text | 1354 | 1300 |
| LMArena Creative Writing | 1340 | 1292 |
| Short-Story Creative Writing | 73.8% | 81.8% |
| WildBench | 80% | 82.8% |
| LMArena Multi-Turn | 1350 | 1302 |
| LiveBench Language | 51.3% | 47.6% |
| EQ-Bench Creative Writing | 1128 | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-4o?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 28.6 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-4o better for coding?
Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.4 versus 24.8 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-4o share?
52 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-4o has 72.