Claude Sonnet 5.5 vs Gemini 4 Neon
TryTop 2 now
Gemini 4 Neon leads by 2.4 capability points (≈95% interval −0.5 to +5.3): statistically tied · P(higher) ≈ 95%
Wins 53 of 62 shared benchmarks (8 lost, 1 tied)
Capability vs. relative cost
Claude Sonnet 5.5Gemini 4 NeonClosed weightsOpen weights
Benchmark wins8 – 53 · 62 shared, 1 tied
Comparing matching setups only (4 benchmarks excluded) · suites counted once
Area← Claude Sonnet 5.5Gemini 4 Neon →
Data: Artificial Analysis, Surge AI, Arena and 12 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Gemini 4 Neon minus Claude Sonnet 5.5.
| Vending-Bench 2 | Business simulations | 11165 | 16843 | +33.6 |
| SimpleQA Verified (Epoch anti-abstention) | Knowledge & reasoning › General knowledge | 46.5 | 75.2 | +28.7 |
| Chess Puzzles (task version 2.0) | Games | 59.0 | 83.0 | +24.0 |
| Mystery Game Puzzles | Games | 65.0 | 85.0 | +20.0 |
| SimpleBench | Knowledge & reasoning › General knowledge | 75.9 | 94.4 | +18.5 |
| SWE-Marathon v1.2 | Software › Software engineering | 80.6 | 62.5 | −18.1 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 53.3 | 71.3 | +18.0 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 52.4 | 70.0 | +17.6 |
| FrontierMath Tier 4 (v2) - Private | Math | 80.5 | 97.6 | +17.1 |
| Terminal-Bench Science 0.1 (Vals) | Science › Multidisciplinary | 47.1 | 62.9 | +15.7 |
| Agents' Last Exam v1.1 Score | Professional › General knowledge work | 60.4 | 75.8 | +15.4 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 35.2 | 49.6 | +14.4 |
| Furniture Assembly Benchmark | Perception & media › Spatial & visual reasoning | 75.0 | 89.2 | +14.2 |
| GDP.xlsx | Professional › General knowledge work | 29.1 | 43.1 | +14.0 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 34.0 | 47.2 | +13.2 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 50.6 | 38.3 | −12.3 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 30.5 | 54.8 | +12.1 |
| Chartography | Perception & media › Documents & charts | 61.6 | 73.5 | +11.9 |
| Artificial Analysis Legal Index | Professional › Legal | 52.2 | 63.8 | +11.6 |
| Bug Hunt Bench | Software › Software engineering | 48.9 | 60.0 | +11.1 |
| CursorBench 4.1 | Software › Software engineering | 54.4 | 65.4 | +11.0 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 76.8 | 87.4 | +10.6 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 40.5 | 50.5 | +10.0 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 41.7 | 31.7 | −10.0 |
| CWE-bench v2 Pass@1 | Software › Cybersecurity | 61.4 | 70.7 | +9.3 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 55.8 | 65.1 | +9.3 |
| HLAB-Vals-1.1 | Professional › Legal | 10.4 | 19.6 | +9.2 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 11.9 | -6.0 | −9.0 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 35.6 | 44.4 | +8.8 |
| Artificial Analysis Engineering Index | Science › Engineering | 58.5 | 66.8 | +8.3 |
| Artificial Analysis Economics Index | Composite indexes | 54.1 | 61.9 | +7.9 |
| LMArena Text Arena Elo | Language & writing › General assistance | 1474 | 1518 | +7.8 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 25.8 | 33.4 | +7.6 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 71.8 | 79.3 | +7.6 |
| RiemannBench (November 2026 rescoring) | Math | 76.8 | 84.0 | +7.2 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 30.7 | 44.5 | +6.9 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 54.5 | 61.4 | +6.9 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 70.8 | 77.4 | +6.6 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 57.1 | 63.6 | +6.6 |
| APEX-Accounting 1.1 | Professional › Finance, accounting & tax | 64.5 | 70.8 | +6.3 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 54.2 | 60.1 | +5.9 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 58.1 | 63.8 | +5.7 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 67.2 | 72.9 | +5.7 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 15.6 | 18.4 | +5.6 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 54.0 | 59.5 | +5.5 |
| APEX-Agents 1.1 | Professional › General knowledge work | 83.7 | 88.9 | +5.2 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 47.7 | 52.3 | +4.6 |
| MKA (Artificial Analysis) | Professional › General knowledge work | 52.0 | 56.5 | +4.5 |
| MysteryMechanism | Math | 49.1 | 45.0 | −4.1 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 14.8 | 21.2 | +3.2 |
| FrontierMath Tiers 1-3 (v2) - Private | Math | 88.8 | 91.2 | +2.5 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 75.1 | 77.4 | +2.3 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 51.2 | 53.4 | +2.2 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1739 | 1699 | −2.2 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 10.8 | 12.8 | +2.0 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 92.4 | 93.7 | +1.3 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1773 | 1764 | −1.2 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 17.6 | 19.2 | +0.8 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 26.8 | 26.2 | −0.6 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 75.9 | 76.5 | +0.6 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | 1.0 | 0.0 |
| OTIS Mock AIME 2024-2025 | Math | 100.0 | 100.0 | 0.0 |
Data: Artificial Analysis, Surge AI, Arena and 12 othersatlas.village.dev