Gemini 3.1 Pro vs Gemini 4 Argon
Gemini 3.1 Pro Verdict
- Gemini 4 Argon (high) leads on quality: 70.0 vs 62.1.
- Gemini 3.1 Pro is stronger in instruction following, long context, multimodal.
- Gemini 4 Argon (high) is stronger in agents & tools, coding, composite, human preference, knowledge, maths, reasoning.
- They cost about the same ($4.00 per 1M blended).
| Metric | Gemini 3.1 Pro | Gemini 4 Argon (high) |
|---|---|---|
| BenchLeader Index | 62.1 | 70.0 |
| Agents & tools score | 56.7 | 67.5 |
| Coding score | 57.3 | 72.1 |
| Composite score | 63.2 | 89.2 |
| Human preference score | 59.5 | 73.2 |
| Instruction following score | 68.4 | – |
| Knowledge score | 64.5 | 75.7 |
| Long context score | 66.3 | 65.0 |
| Maths score | 61.0 | 71.9 |
| Multimodal score | 64.9 | – |
| Reasoning score | 68.6 | 82.0 |
| Blended price $/M | $4.50 | $4.00 |
| Output speed | 114 tok/s | – |
| Time to first answer | 24.8 s | – |
| Context window | 1.0M | 1M |
| GPQA Diamond | 94.1% | – |
| FrontierMath Tiers 1–3 | 59.6% | – |
| FrontierMath Tier 4 | 26.8% | – |
| OTIS Mock AIME | 95.6% | – |
| Humanity's Last Exam | 46.4% | – |
| Terminal-Bench | 80.2% | – |
| SimpleBench | 79.6% | – |
| SciCode | 58.9% | 61.8% |
| WeirdML | 72.1% | – |
| APEX-Agents | 35.3% | – |
| ProofBench | 26.0% | – |
| GSO-Bench | 22.6% | – |
| Epoch Capabilities Index | 154.8 | – |
| LMArena Text | 1487 | 1525 |
| LMArena Hard Prompts | 1508 | 1551 |
| LMArena Coding | 1522 | 1562 |
| LMArena WebDev | 1447 | 1678 |
| LMArena Vision | 1296 | – |
| LMArena Agent | -7.8 | 9.3 |
| AA Intelligence Index v4.3.2 | 29.7 | 52.6 |
| IFBench | 77.1% | – |
| AA-LCR | 82.0% | 79.7% |
| MMMU-Pro | 82.4% | – |
| AA-Omniscience | 31.9 | 42.4 |
| Terminal-Bench Hard | 53.8% | – |
| GPQA Diamond (AA) | 94.1% | – |
| Humanity's Last Exam (AA) | 47.0% | 57.1% |
| SciCode (AA) | 58.7% | 61.8% |
| τ²-Bench Telecom (AA) | 95.6% | – |
| IOI | – | 100.0% |
| LegalBench | – | 88.3% |
| Vals Index | – | 68.9 |
| AIME 2026 | 98.3% | – |
| HMMT February 2026 | 94.7% | – |
| MathArena Apex | 60.9% | – |
| MultiChallenge | 71.4% | – |
| PRBench Finance | 41.9% | – |
| PRBench Legal | 44.0% | – |
| MultiNRC | 64.7% | – |
| HiL-Bench | 35.3% | – |
| TutorBench | 53.0% | – |
| EQ-Bench 4 | 1142 | – |
| ARC-AGI-1 | 98.0% | – |
| ARC-AGI-2 | 77.1% | – |
| ARC-AGI-3 | 0.4% | – |
| CritPt | 17.7% | 27.1% |
| GDPval-AA v2.1 | 14.7% | 56.3% |
| τ³-Banking (AA) | 21.4% | – |
| ITBench SRE (AA) | 30.3% | – |
| Analyst Agent (AA) | 41.3% | – |
| APEX-Agents (AA) | 32.0% | – |
| 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% |
| 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 | 29.8% | – |
| MASK | 42.4% | – |
| SWE Atlas: Codebase QnA | 13.5% | – |
| SWE Atlas: Refactoring | 33.8% | – |
| SWE Atlas: Test Writing | 29.8% | – |
| LMArena Maths | 1488 | 1528 |
| LMArena Creative Writing | 1481 | 1519 |
| LMArena Instruction Following | 1480 | 1529 |
| LMArena Multi-turn | 1497 | 1553 |
| LMArena Longer Queries | 1500 | 1545 |
| LMArena Document | 1459 | – |
| Chess Puzzles | 55.0% | – |
| EBR-bench | 14.3% | – |
| BALROG | 57.0% | – |
| PostTrainBench | 22.0% | – |
| ExploitBench | 26.1% | – |
| CL-bench | 20.8% | – |
| CL-bench Life | 16.9% | – |
| METR Time Horizons | 77.0% | – |
| DeepSWE v1.1 | 11.7% | – |
| ForecastBench | 59.0% | – |
| GBAEval | 0.8% | – |
| ALE-Bench | 1160.6 | – |
| AlgoTune | 2.0 | – |
| Vending-Bench 2 | 911.2 | – |
| Blueprint-Bench 2 | 26.5% | – |
| GDP.pdf | 17.0% | – |
| FrontierSWE | – | 55.0% |
| Terminal-Bench 4.0 (AA) | 4.0% | 57.1% |
| Terminal-Bench 2.1 (AA) | 73.8% | – |
| AutomationBench | 35.4% | 77.5% |
| GDP.pdf | 17.8% | 21.8% |
| MLCR | 15.6% | – |
| Harvey LAB | 0.0% | – |
| EnterpriseOps-Gym | 42.2% | – |
| AA-Omniscience: accuracy | 54.9% | 49.9% |
| AA-Omniscience: non-hallucination | 49.1% | 84.9% |
| AA-Briefcase v1.1 | 456 | 1488 |
| BrowseComp | 31.2% | – |
| DeepSearchQA | 60.2% | – |
| FACTS Search | 83.7% | – |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Gemini 3.1 Pro vs Gemini 4 Argon: questions
- Is Gemini 3.1 Pro better than Gemini 4 Argon?
- Gemini 4 Argon (high) leads on quality: 70.0 vs 62.1. 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 3.1 Pro better than Gemini 4 Argon for coding?
- Gemini 4 Argon scores higher in coding (72 vs 57 on the category index, where 50 is average).
- Is Gemini 3.1 Pro better than Gemini 4 Argon for agentic tasks?
- Gemini 4 Argon scores higher in agentic tasks (68 vs 57 on the category index, where 50 is average).
- Which is cheaper, Gemini 3.1 Pro or Gemini 4 Argon?
- Gemini 4 Argon is cheaper: $4.00 against $4.50 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Gemini 3.1 Pro accepts more context: 1.0M against 1M tokens.