Atlas

Compare Models

Gemini 4 Argon vs Qwen3.8-Max

Gemini 4 Argon leads by 6.3 capability points (≈95% interval +3.7 to +8.8): a clear lead over Qwen3.8-Max · P(higher) ≈ 100%

Wins 22 of 24 shared benchmarks (2 lost)

Capability vs. relative cost
Gemini 4 ArgonQwen3.8-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.

Gemini 4 ArgonvsQwen3.8-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins22 – 2 · 24 shared

Comparing matching setups only (236 benchmarks excluded) · suites counted once
← Gemini 4 ArgonQwen3.8-Max →

Gemini 4 ArgonvsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, AIMING Lab (UNC-Chapel Hill) 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 minus Gemini 4 Argon.

GameBench 2Games89.251.4−37.7
Terminal-Bench 4.0 (Artificial Analysis)Code55.118.7−36.4
AutomationBench-AA 1.0.6Agents77.549.2−28.3
Terminal-Bench 2.1Code57.781.3+23.6
BuseyBench SVGMultimodal7.65.4−21.4
Ramp Accounting BenchFinance & Accounting61.141.2−19.9
AA-Omniscience IndexIndexes42.43.4−19.5
Conceptual Reasoning IndexIndexes72.459.4−17.9
LMCAGeneral QA63.746.2−17.5
RSI-Exam 0.1 (Full 88)Agents0.50.3−17.2
Humanity's Last Exam (Text-Only)General QA57.143.0−14.0
Artificial Analysis Intelligence Index v4.3.2Indexes52.640.2−12.4
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine13.926.1+12.2
SciCode 1.0.1 (Artificial Analysis)Code61.853.2−8.6
Artificial Analysis Progress Index v1Indexes342320−7.8
Epoch Capabilities Index (ECI)Indexes167157−7.3
CritPt (avg@5)Science27.120.0−7.1
MMMU ProMultimodal88.382.3−6.0
ACCoRDGeneral QA77.371.4−5.9
AA-Briefcase v1.1 EloAgents14851382−5.7
DTBenchGeneral QA97.692.0−5.6
GDP.pdf (Artificial Analysis, All-pass)Professional Work25.620.2−5.4
AA-LCR v1.1Search79.778.3−1.3
GDPval-AA v2.1Professional Work16341611−1.0

Gemini 4 ArgonvsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, AIMING Lab (UNC-Chapel Hill) 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…