Benchmark Almanac

TEM-VQA

GPT-4o Mar 2025 40.4 leads since June 2026
Not in model cards

Models give short written answers about structures, image features and experimental design in transmission electron micrographs.

The authors score 2,349 answers with four text similarity metrics. Their source index marks 64 of 261 distinct test images as non-open-access.

Released
June 2026
Kind
Lab and data work
Level
Expert
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 2.5 Flash Sep 2025 #112 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 8 models we track

GPT-4o leads with 40.4 among models released by September 2025 GPT-4o leads with 40.4 among models released by September 2025

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 2025, 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-4o Mar 2025 40.4
  2. 2 Gemini 2.5 Flash Sep 2025 37.7
  3. 3 ATOMIC-7b-Blend 37.5
  4. 4 ATOMIC-13b-Blend 36.6
  5. 5 ATOMIC-Gemma 35.0
  6. 6 llava-v1.5-7b 33.3
  7. 7 Llama 3.2 11B 33.2
  8. 8 LLaVA-v1.5-13B 31.0
  9. 9 Gemma 3 4B 24.2
  10. 10 instructblip-vicuna-7b 12.6
  11. 11 BLIP-2 FLAN-T5-XL 12.3

Source: Official TEM-VQA leaderboard

#EntryScoreSettingDateSource
1 GPT-4o Mar 2025 40.4 Mar 2025 Official leaderboard
2 Gemini 2.5 Flash Sep 2025 37.7 Sep 2025 Official leaderboard
3 ATOMIC-7b-Blend 37.5 Official leaderboard
4 ATOMIC-13b-Blend 36.6 Official leaderboard
5 ATOMIC-Gemma 35.0 Official leaderboard
6 llava-v1.5-7b 33.3 Oct 2023 Official leaderboard
7 Llama 3.2 11B 33.2 Sep 2024 Official leaderboard
8 LLaVA-v1.5-13B 31.0 Oct 2023 Official leaderboard
9 Gemma 3 4B 24.2 Mar 2025 Official leaderboard
10 instructblip-vicuna-7b 12.6 May 2023 Official leaderboard
11 BLIP-2 FLAN-T5-XL 12.3 Feb 2023 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4o Mar 2025 40.4 Mar 2025 Official leaderboard
2 Gemini 2.5 Flash Sep 2025 37.7 Sep 2025 Official leaderboard
3 llava-v1.5-7b 33.3 Oct 2023 Official leaderboard
4 Llama 3.2 11B 33.2 Sep 2024 Official leaderboard
5 LLaVA-v1.5-13B 31.0 Oct 2023 Official leaderboard
6 Gemma 3 4B 24.2 Mar 2025 Official leaderboard
7 instructblip-vicuna-7b 12.6 May 2023 Official leaderboard
8 BLIP-2 FLAN-T5-XL 12.3 Feb 2023 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Not tested since Jun 2026
GPT-4o 40.4

Source: Official TEM-VQA 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
10.0 20.0 30.0 40.0 50.0 2023 2024 2025 10.0 20.0 30.0 40.0 50.0 2023 2024 2025

Source: Official TEM-VQA 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

All 203 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 8 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Flash (#112).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 8 rows for models we track and 3 other entries 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