Claude Opus 5.5 vs Gemini 4 Neon
Gemini 4 Neon leads by 1.3 capability points (≈95% interval −1.6 to +4.3): statistically tied · P(higher) ≈ 82%
Wins 37 of 51 shared benchmarks (11 lost, 3 tied)
Capability vs. relative cost
Claude Opus 5.5Gemini 4 NeonClosed weightsOpen weights
Benchmark wins11 – 37 · 51 shared, 3 tied
Comparing matching setups only (15 benchmarks excluded) · suites counted once
Area← Claude Opus 5.5Gemini 4 Neon →
Data: Surge AI, Arena, Artificial Analysis 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 Opus 5.5.
| Humanity's Sixth Sense | Perception & media › Spatial & visual reasoning | 44.6 | 75.9 | +31.3 |
| SWE-sweep | Software › Software engineering | 10.1 | 39.0 | +28.9 |
| Bug Hunt Bench | Software › Software engineering | 39.7 | 60.0 | +20.3 |
| SWE-Marathon v1.2 | Software › Software engineering | 81.3 | 62.5 | −18.7 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 54.6 | 71.3 | +16.7 |
| Chess Puzzles (task version 2.0) | Games | 67.0 | 83.0 | +16.0 |
| Harvey LAB (Mercor run, undisclosed ~213-task cohort) | Professional › Legal | 10.8 | 26.6 | +15.8 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 34.4 | 49.6 | +15.2 |
| Mystery Game Puzzles | Games | 71.0 | 85.0 | +14.0 |
| GDP.xlsx | Professional › General knowledge work | 30.3 | 43.1 | +12.8 |
| HLAB-Vals-1.1 | Professional › Legal | 9.2 | 19.6 | +10.4 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 14.0 | -6.0 | −10.0 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 64.4 | 72.9 | +8.5 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 61.9 | 70.0 | +8.1 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 42.5 | 50.5 | +8.0 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 46.1 | 38.3 | −7.8 |
| APEX-Agents 1.1 | Professional › General knowledge work | 81.3 | 88.9 | +7.6 |
| CursorBench 4.1 | Software › Software engineering | 58.1 | 65.4 | +7.3 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1818 | 1764 | −7.2 |
| SimpleBench | Knowledge & reasoning › General knowledge | 88.4 | 94.4 | +6.0 |
| Furniture Assembly Benchmark | Perception & media › Spatial & visual reasoning | 83.3 | 89.2 | +5.8 |
| APEX-Accounting 1.1 | Professional › Finance, accounting & tax | 65.5 | 70.8 | +5.3 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 48.8 | 53.4 | +4.6 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 28.8 | 33.4 | +4.6 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 55.0 | 59.5 | +4.5 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 59.6 | 63.6 | +4.0 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 81.4 | 77.4 | −4.0 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 83.4 | 87.4 | +4.0 |
| RiemannBench (November 2026 rescoring) | Math | 80.0 | 84.0 | +4.0 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 27.8 | 31.7 | +3.9 |
| CWE-bench v2 Pass@1 | Software › Cybersecurity | 67.1 | 70.7 | +3.6 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 9.2 | 12.8 | +3.6 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1760 | 1699 | −3.4 |
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 89.6 | 86.6 | −3.0 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 74.4 | 77.4 | +3.0 |
| SimpleQA Verified (Epoch anti-abstention) | Knowledge & reasoning › General knowledge | 72.2 | 75.2 | +3.0 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 38.6 | 44.5 | +2.9 |
| Vals RSI Index v1.1 (four tasks) | Software › Data & ML | 37.3 | 34.4 | −2.9 |
| FrontierMath Tier 4 (v2) - Private | Math | 95.0 | 97.6 | +2.6 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 23.7 | 26.2 | +2.5 |
| LMArena Text Arena Elo | Language & writing › General assistance | 1507 | 1518 | +2.0 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 18.0 | 21.2 | +1.6 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 48.3 | 47.2 | −1.1 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 43.8 | 44.4 | +0.7 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 75.8 | 76.5 | +0.6 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 18.6 | 18.4 | −0.4 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 19.2 | 19.2 | 0.0 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | 1.0 | 0.0 |
| FrontierMath Tiers 1-3 (v2) - Private | Math | 91.2 | 91.2 | 0.0 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 52.3 | 52.3 | 0.0 |
| OTIS Mock AIME 2024-2025 | Math | 100.0 | 100.0 | 0.0 |
Data: Surge AI, Arena, Artificial Analysis and 12 othersatlas.village.dev