Official run

GPT-5.6 LunaHigh

In this Twenty Questions LLM benchmark, GPT-5.6 Luna (high) ranks 16 of 18 with a 17.74 question score and 91% 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 16 of 18openaiHigh

Question score17.74questions · lower is better95% CI 14.74–20.75

Success: 91%
Contract compliance: >99%
Guesser cost: $0.64
Guesser time: 45m 12s

Drill down

Subjects.

01Albert Einstein9.60 avg 02Albert Schweitzer37.40 avg 03Stephen King19.00 avg 04Garfield26.80 avg 05Achilles9.20 avg 06Genghis Khan15.20 avg 07Mario7.00 avg

Complete benchmark

Run ledger.

All Guesser and benchmark-support activity.

Total tokens: 6,336,783
Wall-clock runtime: 2h 47m
Guesser calls: 653
Completed: Jul 28, 2026, 6:53:33 PM

Reliability

Output contract breached.

1 invalid output affected 1 episode and consumed 1 counted turn.

Provenance

Execution: BX-20260728-official-M0001-010
Model ID: M-0001
Benchmark: B-0001
Base seed: 0
Git commit: aa131c32c065

Recorded cost

By role.

Cost composition.Share of full-run cost

Guesser10.9%$0.64
Primary Oracle62%$3.65
Reviewer11.3%$0.67
Judge15.5%$0.91
Validator0.2%$0.01

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.

Read the role and answer-checking method →

Run configuration

Models.

Model identity, prompt versions, routing, calls, and recorded cost for the full run.

GuesserModel under test

openai/gpt-5.6-luna

Asks the questions and submits the scored guess.

Calls: 653
Cost: $0.6431
Reasoning: High
Routing: Exact provider · openai
Resolved model: openai/gpt-5.6-luna
Resolved provider: OpenAI
Prompt contract: stateful-category-guesser-v10-unknown-evidence-guidance
Configuration: M-0001

Resolved provider details

Legacy run. Per-call routing totals were not retained. The configured provider was openai.

Game support

Oracle and adjudication.

These models support the game. They are fixed across the run and are not under test.

Primary Oracle

openai/gpt-5.6-luna

Searches for evidence and proposes an answer.

Calls: 613
Cost: $3.6490
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

Legacy run. Per-call routing totals were not retained. The configured provider was openai.

Reviewer

google/gemini-3.5-flash-lite

Checks each Oracle YES or NO independently.

Calls: 587
Cost: $0.6669
Reasoning: Medium
Routing: Exact provider · google-ai-studio

Resolved provider details

Legacy run. Per-call routing totals were not retained. The configured provider was google-ai-studio.

Judge

anthropic/claude-opus-5

Decides when the Oracle and Reviewer disagree.

Calls: 76
Cost: $0.9122
Reasoning: Medium
Routing: Exact provider · anthropic

Resolved provider details

Legacy run. Per-call routing totals were not retained. The configured provider was anthropic.

Guess Validator

openai/gpt-5.6-luna

Checks a submitted guess against the trusted subject.

Calls: 36
Cost: $0.0109
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

Legacy run. Per-call routing totals were not retained. The configured provider was openai.