Gemini 3 Pro vs Gemini 4 Argon
Gemini 3 Pro Verdict
- Gemini 4 Argon (high) leads on quality: 70.0 vs 60.6.
- Gemini 3 Pro is stronger in instruction following, multimodal.
- Gemini 4 Argon (high) is stronger in agents & tools, coding, human preference, knowledge, maths, reasoning, composite, long context.
| Metric | Gemini 3 Pro | Gemini 4 Argon (high) |
|---|---|---|
| BenchLeader Index | 60.6 | 70.0 |
| Agents & tools score | 61.8 | 67.5 |
| Coding score | 57.9 | 72.1 |
| Human preference score | 68.3 | 73.2 |
| Instruction following score | 61.0 | – |
| Knowledge score | 56.4 | 75.7 |
| Maths score | 54.4 | 71.9 |
| Multimodal score | 65.6 | – |
| Reasoning score | 65.8 | 82.0 |
| Composite score | – | 89.2 |
| Long context score | – | 65.0 |
| Blended price $/M | – | $4.00 |
| Context window | – | 1M |
| GPQA Diamond | 92.6% | – |
| OTIS Mock AIME | 91.4% | – |
| SWE-bench Verified (Epoch) | 72.9% | – |
| Humanity's Last Exam | 37.5% | – |
| Terminal-Bench | 69.4% | – |
| SimpleBench | 76.4% | – |
| GDPval | 40.3% | – |
| SciCode | – | 61.8% |
| Remote Labor Index | 1.3% | – |
| WeirdML | 69.9% | – |
| ProofBench | 20.0% | – |
| GSO-Bench | 18.6% | – |
| Epoch Capabilities Index | 152.9 | – |
| LMArena Text | 1486 | 1525 |
| LMArena Hard Prompts | 1502 | 1551 |
| LMArena Coding | 1517 | 1562 |
| LMArena WebDev | 1440 | 1678 |
| LMArena Vision | 1305 | – |
| LMArena Agent | – | 9.3 |
| AA Intelligence Index v4.3.2 | – | 52.6 |
| AA-LCR | – | 79.7% |
| AA-Omniscience | – | 42.4 |
| Humanity's Last Exam (AA) | – | 57.1% |
| SciCode (AA) | – | 61.8% |
| LiveCodeBench | 86.4% | – |
| MMLU-Pro | 90.1% | – |
| IOI | – | 100.0% |
| LegalBench | – | 88.3% |
| Vals Index | – | 68.9 |
| AIME 2026 | 91.7% | – |
| HMMT February 2026 | 86.4% | – |
| MathArena Apex | 23.4% | – |
| SWE-Bench Pro | 43.3% | – |
| MCP Atlas | 70.3% | – |
| MultiChallenge | 65.7% | – |
| PRBench Finance | 39.2% | – |
| PRBench Legal | 40.6% | – |
| VISTA | 51.5% | – |
| MultiNRC | 59.0% | – |
| TutorBench | 53.7% | – |
| MMMU-Pro (official) | 81.0% | – |
| Kagi LLM Benchmark | 80.1% | – |
| IFEval (HELM) | 87.6% | – |
| Omni-MATH (HELM) | 55.6% | – |
| WildBench (HELM) | 85.9% | – |
| MMLU-Pro (HELM) | 90.3% | – |
| GPQA Diamond (HELM) | 80.3% | – |
| HELM Capabilities mean | 79.9% | – |
| SWE-bench Verified (bash only) | 74.2% | – |
| SWE-bench Verified (any scaffold) | 74.2% | – |
| ARC-AGI-1 | 75.0% | – |
| ARC-AGI-2 | 54.0% | – |
| BFCL Overall | 72.5% | – |
| CritPt | – | 27.1% |
| GDPval-AA v2.1 | – | 56.3% |
| BioMysteryBench | – | 76.3% |
| Code Migration | – | 68.2% |
| CUA-bench | – | 4.8% |
| CyberBench | – | 77.9% |
| Excel Modeling Benchmark | – | 75.2% |
| Finance Agent v2 | – | 65.4% |
| Harvey's Legal Agent Benchmark | – | 19.6% |
| Legal Research Bench | – | 54.8% |
| MedCode | – | 58.8% |
| MedScribe | – | 87.4% |
| MysteryMechanism | – | 45.5% |
| Poker Agent | 1078.9% | – |
| ProgramBench | – | 2.5% |
| Public Benefits Bench | – | 69.8% |
| SAGE | – | 53.6% |
| SREBench | – | 44.3% |
| Tax Agent Bench | – | 76.2% |
| Terminal-Bench 4.0 (Vals) | – | 57.6% |
| Terminal-Bench Science | – | 44.3% |
| Vibe Code Bench v1.1 | – | 91.9% |
| FORTRESS | 41.7% | – |
| MASK | 42.6% | – |
| PropensityBench | 52.9% | – |
| SciPredict | 25.3% | – |
| SWE-Bench Pro (private) | 43.3% | – |
| LMArena Maths | 1477 | 1528 |
| LMArena Creative Writing | 1485 | 1519 |
| LMArena Instruction Following | 1473 | 1529 |
| LMArena Multi-turn | 1496 | 1553 |
| LMArena Longer Queries | 1491 | 1545 |
| LMArena Document | 1451 | – |
| Chess Puzzles | 31.0% | – |
| BALROG | 58.1% | – |
| GeoBench | 84.0% | – |
| VPCT | 91.0% | – |
| CL-bench | 15.8% | – |
| METR Time Horizons | 71.0% | – |
| ForecastBench | 61.2% | – |
| ALE-Bench | 1176.8 | – |
| AlgoTune | 1.8 | – |
| Vending-Bench 2 | 5478.2 | – |
| FrontierSWE | – | 55.0% |
| Terminal-Bench 4.0 (AA) | – | 57.1% |
| AutomationBench | – | 77.5% |
| GDP.pdf | – | 21.8% |
| AA-Omniscience: accuracy | – | 49.9% |
| AA-Omniscience: non-hallucination | – | 84.9% |
| AA-Briefcase v1.1 | – | 1488 |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Gemini 3 Pro vs Gemini 4 Argon: questions
- Is Gemini 3 Pro better than Gemini 4 Argon?
- Gemini 4 Argon (high) leads on quality: 70.0 vs 60.6. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Argon (high) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Gemini 3 Pro better than Gemini 4 Argon for coding?
- Gemini 4 Argon scores higher in coding (72 vs 58 on the category index, where 50 is average).
- Is Gemini 3 Pro better than Gemini 4 Argon for agentic tasks?
- Gemini 4 Argon scores higher in agentic tasks (68 vs 62 on the category index, where 50 is average).