Atlas

Compare Models

GPT-6.1 Sol vs Qwen3.8 Max (0902)

GPT-6.1 Sol leads by 6.0 capability points (≈95% interval +3.4 to +8.5): a clear lead over Qwen3.8 Max (0902) · P(higher) ≈ 100%

Wins 42 of 48 shared benchmarks (6 lost)

Capability vs. relative cost
GPT-6.1 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-6.1 SolvsQwen3.8 Max (0902)capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins42 – 6 · 48 shared

Comparing matching setups only (159 benchmarks excluded) · suites counted once
← GPT-6.1 SolQwen3.8 Max (0902) →

GPT-6.1 SolvsQwen3.8 Max (0902)wins by categoryData Nov 15, 2026Data: Artificial Analysis, BuseyBench, DAXBench and 5 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-6.1 Sol.

AA-PersonalityBench Slop indexChat & Writing14.373.3+59.6
AA-PersonalityBench Transparency indexChat & Writing92.444.8−48.1
Terminal-Bench-Science 0.1Science58.111.9−46.2
Humanity's Last Exam DiamondGeneral QA58.824.0−34.8
CritPt v2 (agentic, avg@5)Science82.651.4−31.1
Code2Video-AA EloCode13691021−28.3
VIALS-AA (pass^3)Multimodal59.031.7−27.3
AA-PersonalityBench Expressiveness indexChat & Writing50.523.8−26.9
Terminal-Bench 4.0Code53.427.0−26.4
AA-3D v1.0 EloCode1121954−24.3
BuseyBench SVGMultimodal8.05.8−21.6
Artificial Analysis Intelligence Index v5.0Indexes54.533.6−21.0
Artificial Analysis Intelligence Index v5.0.1Indexes54.633.7−21.0
Artificial Analysis Engineering IndexIndexes59.439.3−20.1
AA-PersonalityBench Conviction indexChat & Writing54.335.3−19.2
AA-PersonalityBench Warmth indexChat & Writing65.748.6−17.3
FrontierCode 2.0 (Artificial Analysis)Code40.623.4−17.2
Terminal-Bench 4.0 (Artificial Analysis)Code56.138.9−17.2
AA-Omniscience IndexIndexes41.512.0−14.8
CritPt (avg@5)Science31.717.7−14.0
Medical Long Context Reasoning (MLCR-AA)Health & Medicine33.920.0−13.9
VIALS-AA (average of 3)Multimodal64.850.9−13.9
Artificial Analysis Economics IndexIndexes56.342.5−13.8
AA-PersonalityBench Imagination indexChat & Writing61.948.6−13.5
Artificial Analysis Legal IndexIndexes53.741.0−12.7
AA-PersonalityBench Informativeness indexChat & Writing27.739.1+11.5
Artificial Analysis Finance & Accounting IndexIndexes56.245.0−11.2
Artificial Analysis Healthcare & Medical IndexIndexes52.040.8−11.2
Epoch Capabilities Index (ECI)Indexes169156−10.5
AutomationBench-AA 1.0.6Agents66.656.2−10.4
Artificial Analysis Strategy & Ops IndexIndexes57.647.3−10.4
MKA (Artificial Analysis)Professional Work47.737.4−10.3
AA-PersonalityBench Organization indexChat & Writing81.071.4−9.6
DAXBench v2Code92.683.0−9.6
Humanity's Last Exam (Text-Only)General QA52.643.1−9.5
GDP.pdf (Artificial Analysis, All-pass)Professional Work32.022.8−9.2
Artificial Analysis Progress Index v1Indexes348324−8.7
Artificial Analysis Intelligence Index v4.3.2Indexes51.845.4−6.4
FrontierCode 1.1 Main (Artificial Analysis)Code49.143.2−6.0
AA-AnalystAgent (pass^5)Professional Work50.045.0−5.0
SciCode 1.0.1 (Artificial Analysis)Code55.852.1−3.7
AA-LCR v1.1Search84.080.3−3.7
Terminal-Bench 2.1Code85.488.8+3.4
GDPval-AA v2.1Professional Work16071674+2.9
AA-Briefcase v1.1 EloAgents15551604+2.7
MMMU ProMultimodal85.182.8−2.3
Visa Agentic Commerce BenchmarkAgents62.260.0−2.2
VIALS-AA (pass@3)Multimodal70.872.7+1.9

GPT-6.1 SolvsQwen3.8 Max (0902)normalised score marginsData Nov 15, 2026Data: Artificial Analysis, BuseyBench, DAXBench and 5 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…