Benchmark Almanac

RIICHI ORBIT mahjong bot comparison (open practice)

GPT-6 Astra 2.41 leads since September 2026
Not in model cards
Version Open practice

Models get 30 minutes to improve the same mahjong bot, with unlimited practice. The maker freezes each bot before evaluating it on separate tile sequences.

Doui Lab ranks six models by mean placement over 23,040 matches. Each four-model group played the same 64 tile sequences in all 24 seat orders.

Made by
Doui Lab
Released
September 2026
Kind
Building whole projects
Level
University
Scored
Ranked by matches
Answers
Code
Measures
Capability
Language
Japanese
In and out
Text, Code → Code, Actions
Interaction
Agentic
Items from
Generated
Refresh
One fixed set
Run by
A host
In views
Games, Agents
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
6
Models scored on its own leaderboard

GPT-6 Astra leads with 2.41 among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-6 Astra 極高 2.41
  2. 2 GPT-6.1 Sol 極高 2.44
  3. 3 Claude Fable 5.1 超高 2.51
  4. 4 Claude Opus 5.5 超高 2.52
  5. 5 GPT-6 Sol 極高 2.56
  6. 6 GPT-6 Luna 極高 2.57

Source: Official RIICHI ORBIT mahjong bot comparison (open practice) leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 2.41 極高 Sep 2026 Official leaderboard
2 GPT-6.1 Sol 2.44 極高 Sep 2026 Official leaderboard
3 Claude Fable 5.1 2.51 超高 Sep 2026 Official leaderboard
4 Claude Opus 5.5 2.52 超高 Sep 2026 Official leaderboard
5 GPT-6 Sol 2.56 極高 Sep 2026 Official leaderboard
6 GPT-6 Luna 2.57 極高 Sep 2026 Official leaderboard

2 models have held number one on the official leaderboard since its release in September 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic OpenAI
Own leaderboard Replaced by Two-stage practice, Sep 2026

Source: Official RIICHI ORBIT mahjong bot comparison (open practice) leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
2.45 2.50 2.55 2.60 2.45 2.50 2.55 2.60

Source: Official RIICHI ORBIT mahjong bot comparison (open practice) leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

More in Coding

All 523 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471

Data audit

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on note.com: 6 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check