Gemini 4 Hydrogen vs GPT-6.2 Sol
GPT-6.2 Sol leads by 1.3 capability points (≈95% interval −1.4 to +3.9): statistically tied · P(higher) ≈ 82%
Gemini 4 Hydrogen wins 36 of 62 shared benchmarks (26 lost)
Capability vs. relative cost
Gemini 4 HydrogenGPT-6.2 SolClosed weightsOpen weights
Benchmark wins36 – 26 · 62 shared
Comparing matching setups only (33 benchmarks excluded) · suites counted once
Area← Gemini 4 HydrogenGPT-6.2 Sol →
Data: Artificial Analysis, Vals AI, Surge AI and 15 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is GPT-6.2 Sol minus Gemini 4 Hydrogen.
| KradleBench | Games | 43.9 | 67.9 | +24.0 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 9.7 | 32.7 | +23.0 |
| SimpleBench | Knowledge & reasoning › General knowledge | 91.7 | 69.9 | −21.8 |
| GDP.xlsx | Professional › General knowledge work | 40.9 | 22.3 | −18.6 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 49.5 | 66.7 | +17.1 |
| Legal Research Bench | Professional › Legal | 53.8 | 37.0 | −16.8 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 41.2 | 57.3 | +16.0 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 78.4 | 62.9 | −15.5 |
| TaxCalcBench TY25 | Professional › Finance, accounting & tax | 44.0 | 32.0 | −12.0 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 44.6 | 34.5 | −10.1 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 27.2 | 37.2 | +10.0 |
| AutomationBench 1.0.6 (Zapier) | Tool & computer use › Customer service & operations | 51.1 | 41.3 | −9.9 |
| Professional Reasoning Benchmark - Legal | Professional › Legal | 53.1 | 43.3 | −9.7 |
| Vals Finance Index | Professional › Finance, accounting & tax | 66.1 | 56.7 | −9.5 |
| MultiChallenge | Language & writing › Conversation | 80.6 | 72.0 | −8.6 |
| Chartography | Perception & media › Documents & charts | 66.6 | 75.1 | +8.5 |
| Vals Legal Index | Professional › Legal | 73.6 | 66.7 | −7.0 |
| DrugDiscoveryBench | Science › Life sciences | 69.1 | 62.2 | −6.9 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 24.0 | 17.2 | −6.8 |
| ARC-AGI-2 | Knowledge & reasoning › Abstract reasoning | 92.5 | 85.8 | −6.7 |
| Terminal-Bench 4.0 | Software › Software engineering | 54.0 | 60.6 | +6.6 |
| Humanity's Sixth Sense | Perception & media › Spatial & visual reasoning | 63.4 | 56.8 | −6.5 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 65.1 | 58.9 | −6.2 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 33.6 | 27.6 | −6.0 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 38.5 | 32.8 | −5.7 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 54.2 | 48.8 | −5.4 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 58.8 | 64.0 | +5.2 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 54.0 | 58.6 | +4.5 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | -4.5 | 4.3 | +4.4 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 31.7 | 36.1 | +4.4 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 13.5 | 11.3 | −4.3 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 73.7 | 69.5 | −4.2 |
| TxBench Preclinical Pharmacology V1 Clean Reruns | Science › Life sciences | 61.3 | 65.3 | +4.0 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 39.0 | 42.8 | +3.8 |
| Dual-Arm Sim (task completion) | Tool & computer use › Robotics | 0.0 | 3.8 | +3.8 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 77.0 | 80.3 | +3.3 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 74.4 | 71.3 | −3.2 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 29.3 | 23.3 | −3.0 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 46.3 | 40.4 | −2.9 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 32.8 | 30.0 | −2.8 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 82.7 | 85.3 | +2.7 |
| Vals Index v2.2 | Composite indexes | 68.5 | 66.1 | −2.4 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 15.7 | 10.9 | −2.4 |
| Artificial Analysis Economics Index | Composite indexes | 55.0 | 57.4 | +2.3 |
| Gray Swan IPI Attack Success (k=15) | Safety & alignment | 0.0 | 2.3 | −2.3 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 80.6 | 78.3 | −2.3 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 17.4 | 13.4 | −2.0 |
| Artificial Analysis Legal Index | Professional › Legal | 56.7 | 55.0 | −1.7 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 57.7 | 59.4 | +1.7 |
| Ramp SWE-Bench v2 (Bash harness) | Software › Software engineering | 70.8 | 72.4 | +1.6 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 75.8 | 74.3 | −1.5 |
| Agents' Last Exam v1.1 Score | Professional › General knowledge work | 71.6 | 73.0 | +1.4 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 3.6 | 4.8 | +1.2 |
| Artificial Analysis Engineering Index | Science › Engineering | 60.1 | 61.2 | +1.1 |
| ARC-AGI-1 Semi-Private | Knowledge & reasoning › Abstract reasoning | 98.5 | 97.5 | −1.0 |
| DualEntry Accounting AI Benchmark | Professional › Finance, accounting & tax | 83.2 | 84.2 | +1.0 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 58.1 | 57.2 | −0.8 |
| HLAB-Vals-1.1 | Professional › Legal | 11.3 | 12.1 | +0.8 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1569 | 1580 | +0.6 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 0.7 | 1.2 | +0.2 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 87.8 | 87.6 | −0.2 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 53.3 | 53.3 | −0.1 |
Data: Artificial Analysis, Vals AI, Surge AI and 15 othersatlas.village.dev