Model comparison
Gemini 2.0 Flash (Feb 2025) vs Gemini 3 Pro
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 35.1 on the Noometry Index.
Last verified . 36 shared benchmarks.
GoogleSummary
- They share 36 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and Gemini 3 Pro in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 15.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 74.2% for Gemini 3 Pro.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro | |
|---|---|---|
| Provider | ||
| Noometry Index | 35.1 | 54.8 |
| Released | 2024-12-06 | 2025-11-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Gemini 3 Pro: 51.6 (#39)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 74.2% |
| WeirdML | 25.8% | 69.9% |
| LMArena Coding | 1350 | 1481 |
| SWE-bench Verified | — | 72.9% |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1440 |
| SWE-bench Multilingual | — | 68.7% |
| GSO | — | 18.6% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 1,177 |
| AlgoTune | — | 1.83 |
Agentic & Tool Use Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Gemini 3 Pro: 40.6 (#23)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| Terminal-Bench | — | 69.4% |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| GDPval | — | 40.3% |
| Remote Labor Index | — | 1.3% |
| TheAgentCompany | 11.4% | — |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| BALROG | — | 58.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 71% |
| Vending-Bench 2 | — | 5,478 |
Reasoning Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Gemini 3 Pro: 52.5 (#31)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 1.3% | 31.1% |
| SimpleBench | 31.1% | 76.4% |
| Kagi LLM Benchmark | 37.8% | 80.1% |
| EnigmaEval | 1.1% | 18.2% |
| LMArena Hard Prompts | 1346 | 1480 |
| Epoch Capabilities Index | 135.36 | 152.92 |
| NYT Connections (extended) | — | 94.4% |
| ARC-AGI-1 | — | 75% |
| CritPt | — | 6.9% |
| Chess Puzzles | — | 31% |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| ForecastBench | — | 61.2 |
| LiveBench | 66.9% | — |
Math Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Gemini 3 Pro: 49.9 (#59)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 91.4% |
| Omni-MATH | 45.9% | 55.5% |
| LMArena Math | 1352 | 1476 |
| FrontierMath (Feb 2025 set) | 1.7% | 37.6% |
| MathArena Final-Answer Competitions | — | 67% |
| ProofBench | — | 20% |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Gemini 3 Pro: 64.4 (#16)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| GPQA Diamond | 64.1% | 92.6% |
| Humanity's Last Exam | 6.6% | 37.5% |
| MMLU-Pro | 73.7% | 90.3% |
| GPQA (HELM) | 55.6% | 80.3% |
| LMArena Expert | 1339 | 1475 |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 13.6% |
| MMLU | 79.7% | — |
Multimodal Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Gemini 3 Pro: 57.6 (#2)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1158 | 1305 |
| GeoBench | 77% | 84% |
| VPCT | — | 91% |
| LMArena Document | — | 1434 |
Multilingual Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Gemini 3 Pro: 56.9 (#16)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1342 | 1474 |
| LMArena Chinese | 1373 | 1523 |
| LMArena French | 1391 | 1492 |
| LMArena German | 1353 | 1515 |
| LMArena Japanese | 1294 | 1510 |
| LMArena Korean | 1313 | 1448 |
| LMArena Russian | 1351 | 1493 |
| LMArena Spanish | 1363 | 1470 |
Instruction Following Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Gemini 3 Pro: 76.3 (#45)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| IFEval | 84.1% | 87.7% |
| LMArena Instruction Following | 1336 | 1458 |
| LiveBench Instruction Following | 85.8% | — |
Long Context Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Gemini 3 Pro: 44.0 (#79)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1344 | 1471 |
| Fiction.LiveBench | 61.1% | — |
| CL-bench | — | 15.8% |
Writing & Preference Gemini 3 Pro leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Gemini 3 Pro: 66.4 (#35)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1354 | 1479 |
| LMArena Creative Writing | 1340 | 1482 |
| EQ-Bench Creative Writing | 1128 | 1525 |
| WildBench | 80% | 85.9% |
| LMArena Multi-Turn | 1350 | 1484 |
| Short-Story Creative Writing | 73.8% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Gemini 3 Pro?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Gemini 3 Pro better for coding?
Gemini 3 Pro 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 Gemini 3 Pro share?
36 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Gemini 3 Pro has 67.