Official run
Claude Fable 5High
In this Twenty Questions LLM benchmark, Claude Fable 5 (high) ranks 1 of 18 with a 12.06 question score and 100% success. Lower is better. The run contains 35 scored episodes across 7 subjects with 5 trials per subject. Choose a subject to inspect its attempts.
Rank 1 of 18anthropicHigh
- Success
- 100%
- Contract compliance
- 100%
- Guesser cost
- $6.22
- Guesser time
- 1h 9m
Drill down
Subjects.
Complete benchmark
Run ledger.
All Guesser and benchmark-support activity.
- Total tokens
- 3,830,215
- Wall-clock runtime
- 2h 40m
- Guesser calls
- 457
- Completed
Reliability
Output contract clean.
All 457 evaluated outputs matched the public structured-action contract.
Provenance
- Execution
BX-20260805-official-M0014-011- Model ID
M-0014- Benchmark
B-0001- Base seed
0- Git commit
966cbf712380
Recorded cost
By role.
- Guesser79%$6.22
- Primary Oracle11.6%$0.91
- Reviewer4.5%$0.35
- Judge4.8%$0.38
- Validator0%$0.00
Roles in this cost:
- Guesser
- Asks the questions and submits the scored guess.
- Primary Oracle
- Searches for evidence and proposes an answer.
- Reviewer
- Checks each Oracle YES or NO independently.
- Judge
- Decides when the Oracle and Reviewer disagree.
- Validator
- Checks a submitted guess against the trusted subject.
Run configuration
Models.
Model identity, prompt versions, routing, calls, and recorded cost for the full run.
anthropic/claude-fable-5
Asks the questions and submits the scored guess.
- Calls
- 457
- Cost
- $6.2158
- Reasoning
- High
- Routing
- Exact provider · anthropic
- Resolved model
- anthropic/claude-fable-5
- Resolved provider
- Anthropic
- Prompt contract
stateful-category-guesser-v10-unknown-evidence-guidance- Configuration
M-0014
Resolved provider details
- Fallback calls
- 0
- Provider unreported
- 0
Game support
Oracle and adjudication.
These models support the game. They are fixed across the run and are not under test.
openai/gpt-5.6-luna
Searches for evidence and proposes an answer.
- Calls
- 397
- Cost
- $0.9140
- Reasoning
- Medium
- Routing
- Exact provider · openai
- Resolved model
- openai/gpt-5.6-luna
- Resolved provider
- OpenAI
- Prompt contract
live-web-oracle-v7-direct-negative-evidence
Resolved provider details
- Fallback calls
- 0
- Provider unreported
- 0
google/gemini-3.5-flash-lite
Checks each Oracle YES or NO independently.
- Calls
- 379
- Cost
- $0.3531
- Reasoning
- Medium
- Routing
- Exact provider · google-ai-studio
- Resolved provider
- Google AI Studio
Resolved provider details
- Fallback calls
- 0
- Provider unreported
- 0
anthropic/claude-opus-5
Decides when the Oracle and Reviewer disagree.
- Calls
- 33
- Cost
- $0.3797
- Reasoning
- Medium
- Routing
- OpenRouter automatic routing
- Resolved provider
- Amazon Bedrock, Anthropic, Claude Platform on AWS
Resolved provider details
- Fallback calls
- 3
- Provider unreported
- 0
openai/gpt-5.6-luna
Checks a submitted guess against the trusted subject.
- Calls
- 60
- Cost
- $0.0038
- Reasoning
- Medium
- Routing
- Exact provider · openai
- Resolved model
- openai/gpt-5.6-luna
- Resolved provider
- OpenAI
- Prompt contract
strict-guess-validator-v1- Configuration
gpt-5.6-luna-validator
Resolved provider details
- Fallback calls
- 0
- Provider unreported
- 0