Claude Fable 5 vs Qwen3.8-Max
Claude Fable 5 leads by 3.8 capability points (≈95% interval +1.3 to +6.3): a clear lead over Qwen3.8-Max · P(higher) ≈ 100%
Wins 14 of 17 shared benchmarks (3 lost)
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 5vsQwen3.8-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev
Benchmark wins14 – 3 · 17 shared
Claude Fable 5vsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Collinear AI 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 Claude Fable 5.
| Medical Long Context Reasoning (MLCR-AA) | Health & Medicine | 64.4 | 19.4 | −45.0 |
| BabaIsBench Stage 0: The Intro | Games | 100.0 | 58.0 | −42.0 |
| GameBench 2 | Games | 75.2 | 51.4 | −23.8 |
| Terminal-Bench 4.0 (Artificial Analysis) | Code | 42.4 | 18.7 | −23.7 |
| Conceptual Reasoning Index | Indexes | 72.7 | 59.4 | −18.3 |
| LMCA | General QA | 61.1 | 46.2 | −14.9 |
| ACCoRD | General QA | 85.0 | 71.4 | −13.5 |
| MMMU Pro | Multimodal | 72.7 | 82.3 | +9.6 |
| Artificial Analysis Intelligence Index v4.3 | Indexes | 49.7 | 40.3 | −9.4 |
| Humanity's Last Exam (Text-Only) | General QA | 51.5 | 43.0 | −8.5 |
| AA-Briefcase Elo | Agents | 1530 | 1388 | −8.2 |
| Terminal-Bench 2.1 | Code | 88.0 | 81.3 | −6.7 |
| DTBench | General QA | 98.4 | 92.0 | −6.4 |
| SCI-AGENT-EXAM | Science | 67.3 | 62.7 | −4.6 |
| GDPval-AA v2 | Professional Work | 1723 | 1630 | −4.6 |
| YC-Bench | Games | 1977573 | 2095838 | +4.1 |
| OSWorld-Verified | Agents | 86.0 | 86.1 | +0.1 |
Claude Fable 5vsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Collinear AI and 7 othersVillage LLM Atlasatlas.village.dev