Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 35.1 on the Noometry Index.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and GPT-5.2 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 leads 50.2 to 15.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 72.8% for GPT-5.2.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-5.2 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 54.1 |
| Released | 2024-12-06 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 54 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-5.2: 51.6 (#37)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 72.8% |
| WeirdML | 25.8% | 72.2% |
| LMArena Coding | 1350 | 1447 |
| SWE-bench Verified | — | 73.8% |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1416 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
Agentic & Tool Use GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-5.2: 40.2 (#24)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| Terminal-Bench | — | 64.9% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| TheAgentCompany | 11.4% | — |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-5.2: 50.2 (#35)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 52.9% |
| SimpleBench | 31.1% | 45.8% |
| Kagi LLM Benchmark | 37.8% | 73.3% |
| EnigmaEval | 1.1% | 10.4% |
| LMArena Hard Prompts | 1346 | 1445 |
| DTBench | 63.2% | 90.9% |
| Epoch Capabilities Index | 135.36 | 153.45 |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| Chess Puzzles | — | 49% |
| EBR-Bench | — | 23% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 23% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 43.9% |
| ForecastBench | — | 60.1 |
| LiveBench | 66.9% | — |
Math GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-5.2: 60.0 (#38)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 96.1% |
| LMArena Math | 1352 | 1440 |
| FrontierMath (Feb 2025 set) | 1.7% | 40.7% |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| ProofBench | — | 15% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-5.2: 59.3 (#32)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 64.1% | 91.4% |
| Humanity's Last Exam | 6.6% | 27.8% |
| LMArena Expert | 1339 | 1445 |
| SimpleQA Verified | — | 37.1% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 8.4% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-5.2: 51.3 (#7)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1158 | 1268 |
| GeoBench | 77% | — |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-5.2: 53.4 (#67)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1342 | 1425 |
| LMArena Chinese | 1373 | 1460 |
| LMArena French | 1391 | 1455 |
| LMArena German | 1353 | 1448 |
| LMArena Japanese | 1294 | 1420 |
| LMArena Korean | 1313 | 1392 |
| LMArena Russian | 1351 | 1440 |
| LMArena Spanish | 1363 | 1433 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-5.2: 74.7 (#89)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1336 | 1417 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-5.2: 44.0 (#78)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1344 | 1428 |
| Fiction.LiveBench | 61.1% | — |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-5.2: 66.8 (#32)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-5.2 |
|---|---|---|
| LMArena Text | 1354 | 1439 |
| LMArena Creative Writing | 1340 | 1401 |
| EQ-Bench Creative Writing | 1128 | 1703 |
| LMArena Multi-Turn | 1350 | 1458 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-5.2 share?
31 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-5.2 has 67.