- Benchmarks
- 4
- Mappings
- 6
- Rights state
- assumed
machine-ready
runnable-now
- AA-LCR3 mappings
- AA-Omniscience and AA-LCR1 mapping
- Coding and Coding Agent indices1 mapping
- GDPval-AA v21 mapping
Release planning · no model scores
External benchmark evidence map
The provider benchmarks being reviewed for SpringPrompt's V3 business-skill collections, with exact metrics, identity partitions, rights state, and exclusions. No model scores are published here.
These pages document proposed evidence and known exclusions. They do not publish a model order or turn a provider result into a Spring Prompt score.
Sources
25
Registered
10
Benchmark pages
44
V3 mappings
49
Metric fields
57
Provider hierarchy
Sources under review
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
contract-required
contract-required
- AA-Briefcase1 mapping
- AA-Briefcase presentation slices1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
contract-required
contract-required
- APEX-Agents-AA investment banking1 mapping
- APEX-Agents-AA legal1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
contract-required
contract-required
- Harvey LAB-AA1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- approved
machine-ready
runnable-now
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
no-score-feed
no-feed
- BIRD-CRITIC1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 1
- Mappings
- 2
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- DABstep2 mappings
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- Slides and data-visualization arenas1 mapping
- Website and UI arenas1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- approved
rights-review
rights-review
- EQ-Bench 3 workplace scenarios1 mapping
- EQ-Bench message tailoring1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- IFStruct1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 7
- Mappings
- 8
- Rights state
- approved
machine-ready
no-feedrunnable-now
- Agent outcome and steerability1 mapping
- Business and writing preference1 mapping
- Document arena2 mappings
- Search and document arenas1 mapping
- Style-controlled writing and business1 mapping
- Text style-control: business and management1 mapping
- Web development arena1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- approved
machine-ready
runnable-now
- BenchPress observed coding rows1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
rights-review
rights-review
- BizGenEval1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
no-score-feed
no-feed
- Office Comprehension Benchmark1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 3
- Mappings
- 3
- Rights state
- approved
machine-ready
runnable-now
- OpenHands frontend1 mapping
- OpenHands Index1 mapping
- OpenHands information gathering1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- ResearchClawBench1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- SkillsBench1 mapping
- SkillsBench v1.11 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 1
- Mappings
- 2
- Rights state
- not reviewed in source registry
rights-review
rights-review
- SpreadsheetBench V22 mappings
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- approved
machine-ready
runnable-now
- STATE-Bench customer support1 mapping
- STATE-Bench v0.8 main1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- approved
machine-ready
runnable-now
- Structured Output Benchmark1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- approved
machine-ready
runnable-now
- tau2/tau3 support domains1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- approved
machine-ready
runnable-now
- UGI writing components1 mapping
- Benchmarks
- 1
- Mappings
- 1
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- Vectara Hallucination Leaderboard1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
rights-review
rights-review
- WritingBench business and finance1 mapping
- WritingBench business and marketing1 mapping
No attribution link is available in the checked-in source registry. None is inferred.
- Benchmarks
- 2
- Mappings
- 2
- Rights state
- not reviewed in source registry
machine-ready
no-feed
- AutomationBench1 mapping
- AutomationBench Sales and Marketing1 mapping
No attribution link is available in the checked-in source registry. None is inferred.