Atlas

Compare Models

GPT-6 Sol vs Qwen3.8 Max (0902)

GPT-6 Sol leads by 3.4 capability points (≈95% interval +1.1 to +5.8): a clear lead over Qwen3.8 Max (0902) · P(higher) ≈ 100%

Wins 24 of 34 shared benchmarks (10 lost)

Capability vs. relative cost
GPT-6 SolQwen3.8 Max (0902)Closed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

GPT-6 SolvsQwen3.8 Max (0902)capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins24 – 10 · 34 shared

Comparing matching setups only (79 benchmarks excluded) · suites counted once
← GPT-6 SolQwen3.8 Max (0902) →

GPT-6 SolvsQwen3.8 Max (0902)wins by categoryData Nov 15, 2026Data: Artificial Analysis, BuseyBench, Epoch AI and 3 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Qwen3.8 Max (0902) minus GPT-6 Sol.

AA-PersonalityBench Slop indexChat & Writing1.073.3+73.1
AA-PersonalityBench Organization indexChat & Writing12.471.4+59.6
CritPt v2 (agentic, avg@5)Science80.951.4−29.4
AA-PersonalityBench Informativeness indexChat & Writing10.539.1+28.8
AA-3D v1.0 EloCode1131954−25.7
Humanity's Last Exam DiamondGeneral QA45.224.0−21.2
AA-PersonalityBench Imagination indexChat & Writing29.648.6+19.2
Terminal-Bench-Science 0.1Science30.011.9−18.1
BuseyBench SVGMultimodal7.55.8−17.4
Terminal-Bench 4.0Code43.827.0−16.8
AA-PersonalityBench Conviction indexChat & Writing50.535.3−15.4
CritPt (avg@5)Science30.917.7−13.1
FrontierCode 2.0 (Artificial Analysis)Code35.623.4−12.2
Artificial Analysis Intelligence Index v5.0.1Indexes44.233.7−10.5
AA-PersonalityBench Expressiveness indexChat & Writing33.423.8−9.6
ITBench-AAAgents49.440.3−9.2
AA-Omniscience IndexIndexes27.112.0−7.6
GDPval-AA v2.1Professional Work15141674+7.1
AA-Briefcase v1.1 EloAgents14761604+7.0
Epoch Capabilities Index (ECI)Indexes164156−6.6
AA-PersonalityBench Transparency indexChat & Writing39.144.8+5.8
AA-PersonalityBench Warmth indexChat & Writing54.348.6−5.8
SciCode 1.0.1 (Artificial Analysis)Code57.652.1−5.6
AutomationBench-AA 1.0.6Agents61.756.2−5.5
Terminal-Bench 4.0 (Artificial Analysis)Code43.938.9−5.1
Veracode GenAI Code Security (Fall 2026)Cybersecurity73.068.0−5.0
Medical Long Context Reasoning (MLCR-AA)Health & Medicine16.120.0+3.9
Artificial Analysis Progress Index v1Indexes334324−3.6
Terminal-Bench 2.1Code85.488.8+3.4
AA-LCR v1.1Search83.780.3−3.3
Humanity's Last Exam (Text-Only)General QA46.343.1−3.2
GDP.pdf (Artificial Analysis, All-pass)Professional Work25.222.8−2.4
Artificial Analysis Intelligence Index v4.3.2Indexes47.645.4−2.2
MMMU ProMultimodal82.582.8+0.2

GPT-6 SolvsQwen3.8 Max (0902)normalised score marginsData Nov 15, 2026Data: Artificial Analysis, BuseyBench, Epoch AI and 3 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…