Gemini 4 Neon vs GPT-6.1 Sol
Gemini 4 Neon leads by 2.8 capability points (≈95% interval −0.1 to +5.7): statistically tied · P(higher) ≈ 97%
Wins 54 of 63 shared benchmarks (8 lost, 1 tied)
Capability vs. relative cost
Gemini 4 NeonGPT-6.1 SolClosed weightsOpen weights
Benchmark wins54 – 8 · 63 shared, 1 tied
Comparing matching setups only (14 benchmarks excluded) · suites counted once
Area← Gemini 4 NeonGPT-6.1 Sol →
Data: Vals AI, Artificial Analysis, Surge AI and 10 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is GPT-6.1 Sol minus Gemini 4 Neon.
| Humanity's Sixth Sense | Perception & media › Spatial & visual reasoning | 75.9 | 46.6 | −29.3 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 77.4 | 50.3 | −27.1 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 49.6 | 25.2 | −24.4 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 52.3 | 28.6 | −23.7 |
| Vending-Bench 2 | Business simulations | 16843 | 12861 | −23.6 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 47.2 | 25.2 | −22.0 |
| GDP.xlsx | Professional › General knowledge work | 43.1 | 22.0 | −21.1 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 70.0 | 50.5 | −19.5 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 26.6 | 8.8 | −17.8 |
| Legal Research Bench | Professional › Legal | 56.3 | 38.5 | −17.8 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 79.8 | 62.3 | −17.5 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 50.5 | 33.5 | −17.0 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 59.5 | 43.0 | −16.5 |
| APEX-Agents 1.1 | Professional › General knowledge work | 88.9 | 73.2 | −15.7 |
| Chess Puzzles (task version 2.0) | Games | 83.0 | 68.0 | −15.0 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 18.4 | 11.3 | −13.9 |
| HLAB-Vals-1.1 | Professional › Legal | 19.6 | 6.3 | −13.3 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 79.3 | 66.6 | −12.8 |
| Vals Finance Index | Professional › Finance, accounting & tax | 68.3 | 55.8 | −12.5 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 71.3 | 58.8 | −12.5 |
| SimpleBench | Knowledge & reasoning › General knowledge | 94.4 | 82.9 | −11.5 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1699 | 1504 | −10.7 |
| APEX-1 (Mercor, mean score) | Professional › General knowledge work | 79.4 | 69.3 | −10.1 |
| Terminal-Bench Science 0.1 (Vals) | Science › Multidisciplinary | 62.9 | 52.9 | −10.0 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 44.5 | 24.5 | −10.0 |
| Vals Legal Index | Professional › Legal | 78.4 | 68.7 | −9.6 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 63.6 | 54.0 | −9.6 |
| Furniture Assembly Benchmark | Perception & media › Spatial & visual reasoning | 89.2 | 80.0 | −9.2 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 12.8 | 4.0 | −8.8 |
| MKA (Artificial Analysis) | Professional › General knowledge work | 56.5 | 47.7 | −8.8 |
| Vals Index v2.2 | Composite indexes | 70.9 | 63.9 | −6.9 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 61.4 | 54.6 | −6.8 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 68.6 | 61.8 | −6.7 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 31.7 | 38.3 | +6.7 |
| APEX-Accounting 1.1 | Professional › Finance, accounting & tax | 70.8 | 64.3 | −6.5 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 87.4 | 81.2 | −6.3 |
| LMArena Text Arena Elo | Language & writing › General assistance | 1518 | 1483 | −6.2 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 54.8 | 42.4 | −6.2 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 44.4 | 38.5 | −5.9 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | -6.0 | 5.1 | +5.5 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 26.2 | 31.6 | +5.4 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 76.5 | 71.1 | −5.4 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 77.4 | 82.6 | +5.1 |
| Mystery Game Puzzles | Games | 85.0 | 80.0 | −5.0 |
| RiemannBench (November 2026 rescoring) | Math | 84.0 | 79.2 | −4.8 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 93.7 | 88.9 | −4.8 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 21.2 | 11.8 | −4.7 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 38.3 | 33.9 | −4.4 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 19.2 | 11.6 | −3.8 |
| Terminal-Bench 4.0 | Software › Software engineering | 61.6 | 58.2 | −3.4 |
| Agents' Last Exam v1.1 Score | Professional › General knowledge work | 75.8 | 72.5 | −3.3 |
| Vals Science Index | Science › Multidisciplinary | 62.6 | 59.6 | −3.0 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 72.9 | 70.1 | −2.8 |
| FrontierMath Tiers 1-3 (v2) - Private | Math | 91.2 | 93.7 | +2.5 |
| FrontierMath Tier 4 (v2) - Private | Math | 97.6 | 100.0 | +2.4 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 53.4 | 51.6 | −1.8 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 33.4 | 32.0 | −1.4 |
| MysteryMechanism | Math | 45.0 | 46.4 | +1.4 |
| SimpleQA Verified (Epoch anti-abstention) | Knowledge & reasoning › General knowledge | 75.2 | 73.9 | −1.3 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 75.8 | 75.1 | −0.6 |
| BioMysteryBench (Vals Terminus 2) | Science › Life sciences | 80.0 | 79.6 | −0.4 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | 1.2 | +0.1 |
| OTIS Mock AIME 2024-2025 | Math | 100.0 | 100.0 | 0.0 |
Data: Vals AI, Artificial Analysis, Surge AI and 10 othersatlas.village.dev