Atlas

Compare Models

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

GPT-6.1 Terra leads by 5.0 capability points (≈95% interval +2.5 to +7.5): a clear lead over Qwen3.8 Max (0902) · P(higher) ≈ 100%

Wins 32 of 36 shared benchmarks (4 lost)

Capability vs. relative cost
GPT-6.1 TerraQwen3.8 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 TerravsQwen3.8 Max (0902)capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins32 – 4 · 36 shared

Comparing matching setups only (121 benchmarks excluded) · suites counted once
← GPT-6.1 TerraQwen3.8 Max (0902) →

GPT-6.1 TerravsQwen3.8 Max (0902)wins by categoryData Nov 15, 2026Data: Artificial Analysis, BuseyBench, DAXBench and 4 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 Terra.

Terminal-Bench-Science 0.1Science57.611.9−45.7
CritPt v2 (agentic, avg@5)Science81.451.4−30.0
VIALS-AA (pass^3)Multimodal60.231.7−28.6
Terminal-Bench 4.0Code50.327.0−23.3
Humanity's Last Exam DiamondGeneral QA47.324.0−23.3
FrontierCode 2.0 (Artificial Analysis)Code42.323.4−18.9
Artificial Analysis Intelligence Index v5.0.1Indexes51.333.7−17.7
Artificial Analysis Intelligence Index v5.0Indexes51.033.6−17.4
Terminal-Bench 4.0 (Artificial Analysis)Code55.638.9−16.7
Artificial Analysis Engineering IndexIndexes54.739.3−15.5
VIALS-AA (average of 3)Multimodal66.050.9−15.1
BuseyBench SVGMultimodal7.35.8−14.9
AA-Briefcase v1.1 EloAgents14011604+11.1
DAXBench v2Code93.683.0−10.6
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine30.620.0−10.6
CritPt (avg@5)Science28.017.7−10.3
Epoch Capabilities Index (ECI)Indexes168156−9.9
AA-Omniscience IndexIndexes29.812.0−8.9
Visa Agentic Commerce BenchmarkAgents51.160.0+8.9
GDPval-AA v2.1Professional Work14761674+8.7
Artificial Analysis Progress Index v1Indexes345324−7.6
MKA (Artificial Analysis)Professional Work43.837.4−6.3
Artificial Analysis Economics IndexIndexes48.542.5−6.0
GDP.pdf (Artificial Analysis, All-pass)Professional Work28.622.8−5.8
Artificial Analysis Legal IndexIndexes46.441.0−5.4
AutomationBench-AA 1.0.6Agents60.256.2−4.0
Artificial Analysis Finance & Accounting IndexIndexes49.045.0−4.0
Artificial Analysis Healthcare & Medical IndexIndexes44.740.8−3.9
Humanity's Last Exam (Text-Only)General QA46.243.1−3.2
SciCode 1.0.1 (Artificial Analysis)Code55.152.1−3.0
Artificial Analysis Strategy & Ops IndexIndexes50.047.3−2.8
Artificial Analysis Intelligence Index v4.3.2Indexes48.145.4−2.7
AA-LCR v1.1Search82.780.3−2.3
MMMU ProMultimodal84.782.8−1.9
VIALS-AA (pass@3)Multimodal71.472.7+1.2
FrontierCode 1.1 Main (Artificial Analysis)Code43.743.2−0.6

GPT-6.1 TerravsQwen3.8 Max (0902)normalised score marginsData Nov 15, 2026Data: Artificial Analysis, BuseyBench, DAXBench and 4 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…