LABBench2 TableQA2 (image)
Models answer research questions about tables supplied as images.
Edison’s leaderboard compares five distinct models for this task. The suite reports separate results for each input setting.
- Made by
- Edison Scientific
- Released
- February 2026
- Kind
- Research science
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Physical sciences
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- LABBench2
- In views
- Vision
- Strongest model tested
- GPT-5.2 Pro #32 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 21st, 2026
3 models share the top score of 95% among models released by February 2026
Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3 Pro tools,high 95%
- 2 Claude Opus 4.5 tools,high 95%
- 3 GPT-5.2 tools,high 95%
- 4 GPT-5.2 Pro 94%
- 5 Claude Opus 4.6 tools,high 93%
Source: Official LABBench2 TableQA2 (image) leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 95% | tools,high | Nov 2025 | Feb 2026 | Official leaderboard |
| 2 | Claude Opus 4.5 | 95% | tools,high | Nov 2025 | Mar 2026 | Official leaderboard |
| 3 | GPT-5.2 | 95% | tools,high | Dec 2025 | Feb 2026 | Official leaderboard |
| 4 | GPT-5.2 Pro | 94% | Dec 2025 | Feb 2026 | Official leaderboard | |
| 5 | Claude Opus 4.6 | 93% | tools,high | Feb 2026 | Mar 2026 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official LABBench2 TableQA2 (image) leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| tools,high | 95% | 111 | |||
| Claude Opus 4.5 | tools,high | 95% | 353 | ||
| GPT-5.2 | tools,high | 95% | 731 | ||
| GPT-5.2 Pro | 94% | 236 | |||
| GPT-5.2 Pro | tools,high | 94% | 418 | ||
| 93% | 78 | ||||
| GPT-5.2 | 93% | 58 | |||
| Claude Opus 4.6 | tools,high | 93% | 260 | ||
| Claude Opus 4.5 | 92% | 84 | |||
| Claude Opus 4.6 | 91% | 69 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LABBench2 TableQA2 (image) leaderboard
Gemini 3 Pro on the official leaderboard passed 85% in November 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LABBench2 TableQA2 (image) 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 Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (5 entries).
- Pass Models scored 5 models we track.
- Note Newest score The newest came 9 months ago, in February 2026, for Claude Opus 4.6. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.2 Pro (#32).
- Note Headroom Saturated. The best is 95%, past 85% since November 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on advances.edisonscientific.com: 10 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.