Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-5
GPT-5 is the stronger model overall, scoring 50.9 to 35.1 on the Noometry Index.
Last verified . 42 shared benchmarks.
GoogleSummary
- They share 42 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 1 category and GPT-5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 38.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 65% for GPT-5.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-5 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 50.9 |
| Released | 2024-12-06 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 54 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-5: 50.3 (#47)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 65% |
| Aider Polyglot | 38.2% | 88% |
| WeirdML | 25.8% | 60.7% |
| LMArena Coding | 1350 | 1436 |
| SWE-bench Verified | — | 73.6% |
| LMArena WebDev | — | 1418 |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 1,162 |
| AlgoTune | — | 1.67 |
Agentic & Tool Use GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-5: 33.1 (#56)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| Terminal-Bench | — | 49.6% |
| GDPval | — | 34.8% |
| Remote Labor Index | — | 1.7% |
| TheAgentCompany | 11.4% | — |
| DeepResearch Bench | — | 49.6% |
| BALROG | — | 32.8% |
| LMArena Search | — | 1133 |
| METR Time Horizons | — | 69.6% |
Reasoning GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-5: 38.3 (#64)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 9.9% |
| SimpleBench | 31.1% | 56.7% |
| Kagi LLM Benchmark | 37.8% | 72.7% |
| EnigmaEval | 1.1% | 10.5% |
| LMArena Hard Prompts | 1346 | 1416 |
| DTBench | 63.2% | 90.7% |
| Epoch Capabilities Index | 135.36 | 150 |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
| Chess Puzzles | — | 37% |
| EBR-Bench | — | 12.7% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 23% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 40% |
| ForecastBench | — | 61.4 |
| LiveBench | 66.9% | — |
Math GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-5: 55.0 (#44)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 91.4% |
| Omni-MATH | 45.9% | 64.7% |
| LMArena Math | 1352 | 1407 |
| MATH Level 5 | 82.2% | 98.1% |
| FrontierMath (Feb 2025 set) | 1.7% | 32.4% |
| FrontierMath (Tiers 1-3) | — | 55.4% |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 18% |
| LiveBench Math | 75.8% | — |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-5: 56.6 (#43)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| GPQA Diamond | 64.1% | 86.2% |
| Humanity's Last Exam | 6.6% | 25.3% |
| MMLU-Pro | 73.7% | 86.3% |
| Confabulations | 12.4% | 10.3% |
| GPQA (HELM) | 55.6% | 79.2% |
| LMArena Expert | 1339 | 1419 |
| SimpleQA Verified | — | 50.1% |
| Vectara Hallucination Rate | — | 14.7% |
| MMLU | 79.7% | — |
Multimodal GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-5: 46.8 (#13)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| LMArena Vision | 1158 | 1232 |
| GeoBench | 77% | 81% |
| VPCT | — | 66% |
Multilingual GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-5: 51.4 (#110)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| LMArena Non-English | 1342 | 1397 |
| LMArena Chinese | 1373 | 1422 |
| LMArena French | 1391 | 1410 |
| LMArena German | 1353 | 1416 |
| LMArena Japanese | 1294 | 1409 |
| LMArena Korean | 1313 | 1360 |
| LMArena Russian | 1351 | 1406 |
| LMArena Spanish | 1363 | 1399 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-5: 73.8 (#113)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| IFEval | 84.1% | 87.5% |
| LMArena Instruction Following | 1336 | 1388 |
| LiveBench Instruction Following | 85.8% | — |
Long Context GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-5: 69.5 (#2)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| Fiction.LiveBench | 61.1% | 97.2% |
| LMArena Longer Query | 1344 | 1399 |
Writing & Preference GPT-5 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-5: 63.4 (#65)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5 |
|---|---|---|
| LMArena Text | 1354 | 1406 |
| LMArena Creative Writing | 1340 | 1365 |
| Short-Story Creative Writing | 73.8% | 86% |
| EQ-Bench Creative Writing | 1128 | 1627 |
| WildBench | 80% | 85.7% |
| LMArena Multi-Turn | 1350 | 1426 |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-5?
GPT-5 is the stronger model overall, scoring 50.9 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-5 share?
42 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-5 has 69.