Claude Fable 575
- Reasoning
- 93
- Coding
- 70
- Agentic
- 100
- Long context
- 70
83average across 4 tested families
VerdictPal · editorial desk · 2026VerdictPal
Models
Model-first evidence atlas.
We score models, not vendors. Below: every carded model the public benchmark ledger has evidence for, sorted by intelligence receipts (Vals Index first, then Artificial Analysis). Every row carries a date and a URL, not a universal verdict.
Current Vals evidence anchor · Vals Index
Claude Fable 5Anthropic · Claude Fable · 75 on the Vals intelligence index111
Carded models
21
Providers
85
Priced in USD/1M
5
In score ledger only
Models with public intelligence rows
Vals Index rows appear first. Models without a Vals row fall back to Artificial Analysis. Source badges show whether a row is single-source or corroborated — not a cross-benchmark winner.
- 175Vals
- 275Vals
- 373Vals
- 473Vals
- 570Vals
- 668Vals
- 766Vals
- 860Vals
- 956Vals
- 1056Vals
- 1153Vals
- 1251Vals
- 1349Vals
- 1449Vals
- 1548Vals
- 1647Vals
- 1746Vals
- 1841Vals
- 1940Vals
- 2039Vals
- 2135Vals
- 2255AA
- 2354AA
- 2453AA
- 2553AA
- 2651AA
- 2751AA
- 2851AA
- 2951AA
- 3050AA
- 3147AA
- 3247AA
- 3346AA
- 3445AA
- 3544AA
- 3644AA
- 3744AA
- 3844AA
- 3944AA
- 4043AA
- 4143AA
- 4242AA
- 4342AA
- 4442AA
- 4540AA
- 4640AA
- 4739AA
- 4838AA
- 4938AA
- 5037AA
- 5135AA
- 5235AA
- 5334AA
- 5434AA
- 5530AA
- 5630AA
- 5729AA
- 5823AA
- 5922AA
- 6020AA
- 6120AA
- 6218AA
- 6316AA
- 6414AA
- 6513AA
- 6612AA
- 6712AA
- 6810AA
- 698AA
- 708AA
- 715AA
- 725AA
Intelligence × blended cost
Blended cost per million tokens (input + 3× output) on the X axis, log scale. Intelligence index on the Y axis — Vals when present, otherwise Artificial Analysis. Dots are sized by context window and connected by the Pareto frontier (best intelligence at each cost).
All 53 models in this chart
Input-only scatter
The earlier cut, using input cost alone. Useful when your workload is input-heavy (RAG, document Q&A) rather than output-heavy.
Hover or tab any dot for name, score, and input price.
AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere
Every flagship model
5 models with benchmark rows but no card
Older releases, special configurations (Codex CLI, ForgeCode), and ad-hoc aggregations. We surface their sourced scores but we don't promote them to the model atlas until they earn a full model card.
Family radar — strongest current evidence rows
The highest intelligence receipt in each family slice. Use this as a sanity check that a single number isn't hiding a weak spot.
Kimi K375
- Reasoning
- 94
- Coding
- 59
- Agentic
- 85
- Long context
- 75
78average across 4 tested families
Claude Mythos Preview73
- Reasoning
- 95
- Coding
- 94
- Agentic
- 84
91average across 3 tested families
Which families does the ledger actually cover?
A model with no row in a family is a model that hasn't been publicly tested there. We surface that instead of pretending it's weak.
Knowledge30models covered
Reasoning74models covered
Math25models covered
Coding74models covered
Agentic71models covered
Multimodal8models covered
Long context69models covered
Tool use20models covered
Performance0models covered
Safety9models covered
Human preference13models covered
Where these models show up in the card atlas
Every tool card on this list is wired to at least one model in the atlas above. The same wrapper that hides the harness can also hide the price.