Official run

GPT-6 AstraHigh

In this Twenty Questions AI benchmark, GPT-6 Astra (high) ranks 1 of 21 with a question score of 13.67: the average number of questions per round, where lower is better. It solved every round. The run has 30 scored rounds: 10 subjects, 3 rounds each. Choose a subject to see its rounds.

Rank 1 of 21openaiHigh

Question score13.67questions per roundLower is better · 95% CI 12.49–14.85

Solved: 100%
Valid format: 100%
Guesser cost: $5.27
Guesser time: 40m 43s

Drill down

Subjects.

01Albert Einstein9.67 avg 02Albert Schweitzer16.00 avg 03Garfield8.00 avg 04Achilles8.00 avg 05Genghis Khan10.00 avg 06Bike pump26.33 avg 07Spider web18.33 avg 08Eyebrow12.67 avg 09Moon10.00 avg 10Door handle17.67 avg

Complete benchmark

Run totals.

Includes the Guesser and all answer-checking models.

Total tokens: 3,043,336
Total runtime: 1h 58m
Guesser calls: 440
Completed: 9 Sep 2026, 08:31 UTC

Reply format

No format errors.

All 440 checked replies used the required format.

Run details

Execution: BX-20260909-B-0003-experimental-M0022-002
Model ID: M-0022
Benchmark: B-0003
Base seed: 0
Git commit: 2d5409df2ba6

Recorded cost

By role.

Cost composition.Share of full-run cost

Guesser78.8%$5.27
Oracle11.2%$0.75
Reviewer5.4%$0.36
Judge4.5%$0.30
Validator0.1%$0.01

Rerun cost (excluded)$0.171 earlier attempt in 1 rerun round. Not included above.

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.

How the roles and answer checks work →

Run configuration

Models.

Models, prompt versions, providers, calls, and cost for the whole run.

GuesserModel under test

openai/gpt-6-astra

The tested model. Asks questions and makes guesses.

Calls: 440
Cost: $5.2672
Reasoning: High
Routing: Fixed provider · openai
Resolved model: openai/gpt-6-astra
Resolved provider: OpenAI
Prompt version: stateful-category-guesser-v16-five-answer-category-guide
Configuration: M-0022

Provider details

OpenAI440 calls$5.26722,443.18 s

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.

Oracle

openai/gpt-5.6-luna

Searches for evidence and proposes an answer.

Calls: 271
Cost: $0.7492
Reasoning: Medium
Routing: Fixed provider · openai
Resolved model: openai/gpt-5.6-luna
Resolved provider: OpenAI
Prompt version: live-web-oracle-v17-labelled-source-context

Provider details

OpenAI271 calls$0.74922,513.18 s

Fallback calls: 0
Provider not reported: 0

Reviewer

google/gemini-3.5-flash-lite

Checks each Oracle answer except Unknown, without seeing it.

Calls: 258
Cost: $0.3588
Reasoning: Medium
Routing: Fixed provider · google-ai-studio
Resolved provider: Google AI Studio

Provider details

Google AI Studio258 calls$0.3588447.59 s

Fallback calls: 0
Provider not reported: 0

Judge

anthropic/claude-opus-5

Decides when the Oracle and Reviewer disagree.

Calls: 12
Cost: $0.3026
Reasoning: Medium
Routing: Chosen automatically by OpenRouter
Resolved provider: Claude Platform on AWS

Provider details

Claude Platform on AWS12 calls$0.3026100.37 s

Fallback calls: 0
Provider not reported: 0

Guess Validator

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

OpenAI32 calls$0.006257.58 s

Fallback calls: 0
Provider not reported: 0