Official run

GPT-6 SolHigh

In this Twenty Questions LLM benchmark, GPT-6 Sol (high) ranks 9 of 18 with a 18.03 question score and 100% success. Lower is better. The run contains 30 scored episodes across 10 subjects with 3 trials per subject. Choose a subject to inspect its attempts.

Rank 9 of 18openaiHigh

Question score18.03questions · lower is better95% CI 16.29–19.77

Success: 100%
Contract compliance: 100%
Guesser cost: $1.19
Guesser time: 32m 3s

Drill down

Subjects.

01Albert Einstein11.33 avg 02Albert Schweitzer31.33 avg 03Garfield13.00 avg 04Achilles9.00 avg 05Genghis Khan12.67 avg 06Bike pump34.00 avg 07Spider web17.00 avg 08Eyebrow13.33 avg 09Moon8.33 avg 10Door handle30.33 avg

Complete benchmark

Run ledger.

All Guesser and benchmark-support activity.

Total tokens: 4,103,559
Wall-clock runtime: 1h 37m
Guesser calls: 571
Completed: Sep 26, 2026, 8:31:33 PM

Reliability

Output contract clean.

All 571 evaluated outputs matched the public structured-action contract.

Run details

Execution: BX-20260926-B-0003-official-M0029-001
Model ID: M-0029
Benchmark: B-0003
Base seed: 0
Git commit: 6e46fb003ebf

Recorded cost

By role.

Cost composition.Share of full-run cost

Guesser35.6%$1.19
Primary Oracle30.6%$1.02
Reviewer16.4%$0.55
Judge17.3%$0.58
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-6-sol

Asks the questions and submits the scored guess.

Calls: 571
Cost: $1.1933
Reasoning: High
Routing: Exact provider · openai
Resolved model: openai/gpt-6-sol
Resolved provider: OpenAI
Prompt contract: stateful-category-guesser-v16-five-answer-category-guide
Configuration: M-0029

Resolved provider details

OpenAI571 calls$1.19331,923.00 s

Fallback calls: 0
Provider unreported: 0

Game support

Answering and checking models.

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: 416
Cost: $1.0232
Reasoning: Medium
Routing: Exact provider · openai
Resolved model: openai/gpt-5.6-luna
Resolved provider: OpenAI
Prompt contract: live-web-oracle-v17-labelled-source-context

Resolved provider details

OpenAI416 calls$1.02322,958.48 s

Fallback calls: 0
Provider unreported: 0

Reviewer

google/gemini-3.5-flash-lite

Checks each Oracle YES or NO independently.

Calls: 405
Cost: $0.5477
Reasoning: Medium
Routing: Exact provider · google-ai-studio
Resolved provider: Google AI Studio

Resolved provider details

Google AI Studio405 calls$0.5477688.28 s

Fallback calls: 0
Provider unreported: 0

Judge

anthropic/claude-opus-5

Decides when the Oracle and Reviewer disagree.

Calls: 27
Cost: $0.5775
Reasoning: Medium
Routing: OpenRouter automatic routing
Resolved provider: Claude Platform on AWS

Resolved provider details

Claude Platform on AWS27 calls$0.5775155.82 s

Fallback calls: 0
Provider unreported: 0

Guess Validator

openai/gpt-5.6-luna

Checks a submitted guess against the trusted subject.

Calls: 31
Cost: $0.0059
Reasoning: Medium
Routing: Exact provider · openai
Resolved model: openai/gpt-5.6-luna
Resolved provider: OpenAI
Prompt contract: strict-guess-validator-v2-generic-kinds
Configuration: gpt-5.6-luna-validator

Resolved provider details

OpenAI31 calls$0.005947.15 s

Fallback calls: 0
Provider unreported: 0