Official run
Claude Opus 5High
In this Twenty Questions AI benchmark, Claude Opus 5 (high) ranks 11 of 21 with a question score of 18.07: the average number of questions per round, where lower is better. It failed 2 of 30 rounds. The run has 30 scored rounds: 10 subjects, 3 rounds each. Choose a subject to see its rounds.
Rank 11 of 21anthropicHigh
Round scores are averaged for each subject, then across subjects. A failed round gets the fixed failure score.
The 95% confidence interval shows how certain the average is, based on repeated rounds on these subjects. A wider interval means less consistent results. It does not predict scores on other subjects.
- Solved
- 93%
- Valid format
- 99.6%
- Guesser cost
- $2.80
- Guesser time
- 41m 2s
Drill down
Subjects.
Complete benchmark
Run totals.
Includes the Guesser and all answer-checking models.
- Total tokens
- 5,842,602
- Total runtime
- 20h 9m
- Guesser calls
- 570
- Completed
Reply format
Format errors found.
2 invalid replies in 1 round used up 2 counted turns.
Run details
- Execution
BX-20260907-B-0003-experimental-M0006-002- Model ID
M-0006- Benchmark
B-0003- Base seed
0- Git commit
04dde57c3906
Recorded cost
By role.
- Guesser50.5%$2.80
- Oracle25.8%$1.43
- Reviewer10.8%$0.60
- Judge12.9%$0.72
- Validator0.1%$0.01
Roles in this cost:
- Guesser
- The tested model. Asks questions and makes guesses.
- Oracle
- Searches for evidence and proposes an answer.
- Reviewer
- Checks each Oracle answer except Unknown, without seeing it.
- Judge
- Decides when the Oracle and Reviewer disagree.
- Validator
- Checks whether a guess names the hidden subject.
Run configuration
Models.
Models, prompt versions, providers, calls, and cost for the whole run.
anthropic/claude-opus-5
The tested model. Asks questions and makes guesses.
- Calls
- 570
- Cost
- $2.8025
- Reasoning
- High
- Routing
- Fixed provider · anthropic
- Resolved model
- anthropic/claude-opus-5
- Resolved provider
- Anthropic
- Prompt version
stateful-category-guesser-v16-five-answer-category-guide- Configuration
M-0006
Provider details
- Fallback calls
- 0
- Provider not reported
- 0
Answer checks
Answering and checking models.
These models answer and check the Guesser's questions and guesses. They are the same for every round and are not being tested.
openai/gpt-5.6-luna
Searches for evidence and proposes an answer.
- Calls
- 535
- Cost
- $1.4306
- Reasoning
- Medium
- Routing
- Fixed provider · openai
- Resolved model
- openai/gpt-5.6-luna
- Resolved provider
- OpenAI
- Prompt versions
live-web-oracle-v16-search-headroomlive-web-oracle-v17-labelled-source-context
Provider details
- Fallback calls
- 0
- Provider not reported
- 0
google/gemini-3.5-flash-lite
Checks each Oracle answer except Unknown, without seeing it.
- Calls
- 485
- Cost
- $0.5992
- Reasoning
- Medium
- Routing
- Fixed provider · google-ai-studio
- Resolved provider
- Google AI Studio
Provider details
- Fallback calls
- 0
- Provider not reported
- 0
anthropic/claude-opus-5
Decides when the Oracle and Reviewer disagree.
- Calls
- 36
- Cost
- $0.7164
- Reasoning
- Medium
- Routing
- Chosen automatically by OpenRouter
- Resolved provider
- Claude Platform on AWS
Provider details
- Fallback calls
- 0
- Provider not reported
- 0
openai/gpt-5.6-luna
Checks whether a guess names the hidden subject.
- Calls
- 32
- Cost
- $0.0062
- Reasoning
- Medium
- Routing
- Fixed provider · openai
- Resolved model
- openai/gpt-5.6-luna
- Resolved provider
- OpenAI
- Prompt version
strict-guess-validator-v2-generic-kinds- Configuration
gpt-5.6-luna-validator
Provider details
- Fallback calls
- 0
- Provider not reported
- 0