Atlas

Compare Models

GPT-6 Sol vs Qwen3.8-Max

GPT-6 Sol leads by 4.1 capability points (≈95% interval +1.6 to +6.6): a clear lead over Qwen3.8-Max · P(higher) ≈ 100%

Wins 23 of 27 shared benchmarks (4 lost)

Capability vs. relative cost
GPT-6 SolQwen3.8-MaxClosed 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-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins23 – 4 · 27 shared

Comparing matching setups only (231 benchmarks excluded) · suites counted once
← GPT-6 SolQwen3.8-Max →

GPT-6 SolvsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Vercel and 7 othersVillage LLM Atlasatlas.village.dev

Margins

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

Cresta-BenchAgents77.948.7−29.3
GameBench 2Games79.451.4−28.0
DeepsecBench — Revalidated V1Code40.915.5−25.4
DeepsecBench — Revalidated V1 (233 issues)Code40.715.5−25.3
Terminal-Bench 4.0 (Artificial Analysis)Code43.918.7−25.3
YC-BenchGames14417932095838+22.8
BuseyBench SVGMultimodal7.55.4−21.1
Conceptual Reasoning IndexIndexes71.059.4−16.1
LMCAGeneral QA59.146.2−12.8
AutomationBench-AA 1.0.6Agents61.749.2−12.5
AA-Omniscience IndexIndexes27.13.4−11.9
ACCoRDGeneral QA82.471.4−11.0
CritPt (avg@5)Science30.920.0−10.9
Artificial Analysis Intelligence Index v4.3.2Indexes47.640.2−7.5
AA-LCR v1.1Search83.778.3−5.3
DTBenchGeneral QA97.392.0−5.3
Epoch Capabilities Index (ECI)Indexes164157−5.3
AA-Briefcase v1.1 EloAgents14761382−5.2
Artificial Analysis Progress Index v1Indexes334320−5.1
GDP.pdf (Artificial Analysis, All-pass)Professional Work25.220.2−5.0
SciCode 1.0.1 (Artificial Analysis)Code57.653.2−4.4
GDPval-AA v2.1Professional Work15141611+4.3
Terminal-Bench 2.1Code85.481.3−4.1
Medical Long Context Reasoning (MLCR-AA)Health & Medicine16.119.4+3.3
Humanity's Last Exam (Text-Only)General QA46.343.0−3.2
Nimble Web ContextSearch76.577.3+0.8
MMMU ProMultimodal82.582.3−0.2

GPT-6 SolvsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Vercel and 7 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…