Benchmark Almanac

Table Judge Benchmark

Claude Opus 4.8 94.9% leads since May 2026
Not in model cards

Vision language models judge whether rendered table images match candidate HTML. Controlled corruptions test false positives, true positives and injected-error detection.

The release has 538 clean pairs, 538 corrupted pairs and eight frontier judge models. It reports false-positive rate, true-positive rate, F1 and detection of the injected rubric.

Made by
Reducto
Released
November 2025
Kind
Documents, charts and text in images
Level
Expert
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Documents → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
GPT-5.6 Sol #14 on the capability index
Last model added
July 2026
Scores refreshed
November 21st, 2026
8
Models scored in its paper

Claude Opus 4.8 leads with 94.9% among models released by July 2026

Best score per model from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The benchmark table ranks judges by F1, the harmonic mean of precision and true positive rate. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in July 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 Claude Opus 4.8 94.9%
  2. 2 Claude Opus 4.7 93.1%
  3. 3 GPT-5.5 92.3%
  4. 4 GPT-5.6 Sol 91.4%
  5. 5 Gemini 3.1 Pro 90.9%
  6. 6 GPT-5.6 Terra 90.8%
  7. 7 GPT-5.4 88.3%
  8. 8 GPT-5.6 Luna 86.1%

Source: The Table Judge Benchmark paper

#ModelScoreSettingDateSource
1 Claude Opus 4.8 94.9% May 2026 Official leaderboard
2 Claude Opus 4.7 93.1% Apr 2026 Official leaderboard
3 GPT-5.5 92.3% Apr 2026 Official leaderboard
4 GPT-5.6 Sol 91.4% Jul 2026 Official leaderboard
5 Gemini 3.1 Pro 90.9% Feb 2026 Official leaderboard
6 GPT-5.6 Terra 90.8% Jul 2026 Official leaderboard
7 GPT-5.4 88.3% Mar 2026 Official leaderboard
8 GPT-5.6 Luna 86.1% Jul 2026 Official leaderboard

3 models have held number one in the benchmark’s paper since its release in November 2025

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

Google DeepMind Anthropic
Benchmark paper Passed 85% in Feb 2026, by Gemini 3.1 Pro

Source: The Table Judge Benchmark paper

Gemini 3.1 Pro on the official leaderboard passed 85% in February 2026

That was 3 months after its release. By the same age, 12% of the benchmarks from 2025 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.8 Gemini 3.1 Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.8

Source: Official Table Judge Benchmark 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 Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

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 benchmark’s paper (8 entries).
  • Pass Models scored 8 models we track.
  • Pass Newest score The newest is from July 2026, for GPT-5.6 Luna.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.6 Sol (#14).
  • Note Headroom Saturated. The best is 94.9%, past 85% since February 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 8 rows for models we track at the last read.
  • Pass Last read November 21st, 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