Atlas

Compare Models

Claude Fable 5.1 vs Qwen3.8 Max (0902)

Claude Fable 5.1 leads by 5.4 capability points (≈95% interval +2.9 to +7.9): a clear lead over Qwen3.8 Max (0902) · P(higher) ≈ 100%

Wins 30 of 35 shared benchmarks (5 lost)

Capability vs. relative cost
Claude Fable 5.1Qwen3.8 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.

Claude Fable 5.1vsQwen3.8 Max (0902)capability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins30 – 5 · 35 shared

Comparing matching setups only (67 benchmarks excluded) · suites counted once
← Claude Fable 5.1Qwen3.8 Max (0902) →

Claude Fable 5.1vsQwen3.8 Max (0902)wins by categoryData Nov 15, 2026Data: Artificial Analysis, Mercor, AIMING Lab (UNC-Chapel Hill) 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 (0902) minus Claude Fable 5.1.

AA-PersonalityBench Expressiveness indexChat & Writing98.123.8−75.0
AA-PersonalityBench Conviction indexChat & Writing10035.3−65.4
AA-PersonalityBench Informativeness indexChat & Writing96.239.1−57.7
AA-PersonalityBench Transparency indexChat & Writing98.144.8−53.8
Medical Long Context Reasoning (MLCR-AA)Health & Medicine71.120.0−51.1
AA-PersonalityBench Slop indexChat & Writing23.873.3+50.0
AA-PersonalityBench Warmth indexChat & Writing94.348.6−46.2
AA-PersonalityBench Imagination indexChat & Writing86.748.6−38.5
SPU (Science Prediction Universe)Science-0.50.1+32.4
Terminal-Bench 4.0Code57.927.0−30.9
AA-3D v1.0 EloCode1139954−26.9
CritPt v2 (agentic, avg@5)Science77.751.4−26.3
Code2Video-AA EloCode13251021−24.7
Last Translation Benchmark (LTBv1-eval, blind)Chat & Writing32.912.5−20.4
Visa Agentic Commerce BenchmarkAgents75.660.0−15.6
CritPt (avg@5)Science31.117.7−13.4
AA-AnalystAgent (pass^5)Professional Work57.545.0−12.5
BuseyBench SVGMultimodal7.05.8−12.4
AA-PersonalityBench Organization indexChat & Writing60.071.4+11.5
Humanity's Last Exam (Text-Only)General QA54.643.1−11.5
SciCode 1.0.1 (Artificial Analysis)Code63.152.1−11.0
ITBench-AAAgents49.540.3−9.3
Epoch Capabilities Index (ECI)Indexes167156−9.1
RSI-Exam 0.1 (Full 88)Agents0.50.4−8.9
DAXBench v2Code91.583.0−8.5
Artificial Analysis Intelligence Index v4.3Indexes53.445.4−7.9
AA-LCR v1.1Search87.580.3−7.2
Terminal-Bench 2.1Code81.688.8+7.2
FrontierCode 2.0 (Artificial Analysis)Code30.323.4−6.9
FrontierCode 1.1 Main (Artificial Analysis)Code49.043.2−5.8
GDPval-AA v2.1Professional Work17651674−4.0
GDPval-AA v2Professional Work17641689−3.7
MMMU ProMultimodal86.182.8−3.3
AA-Briefcase EloAgents16621622−2.3
Harvey LAB-AA v1.0 (criterion pass rate)Legal93.393.6+0.4

Claude Fable 5.1vsQwen3.8 Max (0902)normalised score marginsData Nov 15, 2026Data: Artificial Analysis, Mercor, AIMING Lab (UNC-Chapel Hill) 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…