Official run

GPT-5.6 SolHigh

In this Twenty Questions LLM benchmark, GPT-5.6 Sol (high) ranks 9 of 18 with a 14.40 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 9 of 18openaiHigh

Question score14.40questions · lower is better95% CI 12.84–15.96

Success: 100%
Contract compliance: 100%
Guesser cost: $5.99
Guesser time: 1h 19m

Drill down

Subjects.

01Albert Einstein12.20 avg 02Albert Schweitzer22.40 avg 03Stephen King23.20 avg 04Garfield13.40 avg 05Achilles7.40 avg 06Genghis Khan13.20 avg 07Mario9.00 avg

Complete benchmark

Run ledger.

All Guesser and benchmark-support activity.

Total tokens: 6,033,844
Wall-clock runtime: 2h 57m
Guesser calls: 539
Completed: Jul 28, 2026, 10:03:15 PM

Reliability

Output contract clean.

All 539 evaluated outputs matched the public structured-action contract.

Provenance

Execution: BX-20260728-official-M0010-010
Model ID: M-0010
Benchmark: B-0001
Base seed: 0
Git commit: c5358232b0d9

Recorded cost

By role.

Cost composition.Share of full-run cost

Guesser60%$5.99
Primary Oracle32.2%$3.21
Reviewer4.1%$0.41
Judge3.6%$0.35
Validator0.1%$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-sol

Asks the questions and submits the scored guess.

Calls: 539
Cost: $5.9877
Reasoning: High
Routing: Exact provider · openai
Resolved model: openai/gpt-5.6-sol
Resolved provider: OpenAI
Prompt contract: stateful-category-guesser-v10-unknown-evidence-guidance
Configuration: M-0010

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: 496
Cost: $3.2102
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: 459
Cost: $0.4072
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: 26
Cost: $0.3541
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: 43
Cost: $0.0134
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.