Benchmark Almanac

Grade Your Own Homework: Can LLMs Judge Each Other

Gemini 3.7 Flash 0.97 leads since October 2026
Not in model cards

Models solve problems and grade answers, including their own. The benchmark varies answer order, author names, and stated confidence against labels computed by code.

Kaggle publishes scores for 10 distinct model versions.

Made by
Anish_23101
Released
October 2026
Kind
Language reasoning
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Propensity
Behavior
Unreliability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 3.8 Flash #24 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 9 models we track

Gemini 3.7 Flash leads with 0.97 among models released by September 2026 Gemini 3.7 Flash leads with 0.97 among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at 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 Gemini 3.7 Flash 0.97
  2. 2 Gemini 3.8 Flash 0.95
  3. 3 Gemma 4 31B IT 0.88
  4. 4 GLM-5 0.84
  5. 5 Claude Haiku 4.5 0.64
  6. 6 Gemini 3.5 Flash-Lite 0.60
  7. 7 Qwen 3 235B A22B Instruct 2506 0.56
  8. 8 GPT-5.4 Mini 0.51
  9. 9 Grok 4.20 non-reasoning 0.49
  10. 10 GPT-5.4 Nano 0.38

Source: Official Grade Your Own Homework: Can LLMs Judge Each Other leaderboard

#EntryScoreSettingReleasedRun onSource
1 Gemini 3.7 Flash 0.97 Aug 2026 Oct 2026 Official leaderboard
2 Gemini 3.8 Flash 0.95 Sep 2026 Oct 2026 Official leaderboard
3 Gemma 4 31B IT 0.88 Apr 2026 Oct 2026 Official leaderboard
4 GLM-5 0.84 Feb 2026 Oct 2026 Official leaderboard
5 Claude Haiku 4.5 0.64 Oct 2025 Oct 2026 Official leaderboard
6 Gemini 3.5 Flash-Lite 0.60 Jul 2026 Oct 2026 Official leaderboard
7 Qwen 3 235B A22B Instruct 2506 0.56 Oct 2026 Official leaderboard
8 GPT-5.4 Mini 0.51 Mar 2026 Oct 2026 Official leaderboard
9 Grok 4.20 0.49 non-reasoning Feb 2026 Oct 2026 Official leaderboard
10 GPT-5.4 Nano 0.38 Mar 2026 Oct 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Gemini 3.7 Flash 0.97 Aug 2026 Oct 2026 Official leaderboard
2 Gemini 3.8 Flash 0.95 Sep 2026 Oct 2026 Official leaderboard
3 Gemma 4 31B IT 0.88 Apr 2026 Oct 2026 Official leaderboard
4 GLM-5 0.84 Feb 2026 Oct 2026 Official leaderboard
5 Claude Haiku 4.5 0.64 Oct 2025 Oct 2026 Official leaderboard
6 Gemini 3.5 Flash-Lite 0.60 Jul 2026 Oct 2026 Official leaderboard
7 GPT-5.4 Mini 0.51 Mar 2026 Oct 2026 Official leaderboard
8 Grok 4.20 0.49 non-reasoning Feb 2026 Oct 2026 Official leaderboard
9 GPT-5.4 Nano 0.38 Mar 2026 Oct 2026 Official leaderboard

Number one over time

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

Google DeepMind
Own leaderboard Not tested since Oct 2026

Source: Official Grade Your Own Homework: Can LLMs Judge Each Other 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
0.40 0.60 0.80 1.00 2026 0.40 0.60 0.80 1.00 2026

Source: Official Grade Your Own Homework: Can LLMs Judge Each Other 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.

More in Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.8 Flash (#24).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 9 rows for models we track and 1 other entry 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