Benchmark Almanac

Bio-VQA

InternVL3-38B 0.91 leads since August 2026
Not in model cards

Models identify organisms, describe visible traits, judge spatial relationships, and recognize individual animals across photographs. The benchmark has 24 tasks.

Passes test 2. The authors publish scores for 18 general vision-language models and release their individual answers. Each task has its own scoring rule.

Released
August 2026
Kind
General visual questions
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
Last model added
June 2026
Scores refreshed
November 20th, 2026
18
Entries on its own leaderboard, 17 models we track

InternVL3-38B leads with 0.91 among models released by June 2026 InternVL3-38B leads with 0.91 among models released by June 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 June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: Official Bio-VQA leaderboard

#EntryScoreSettingDateSource
1 InternVL3-38B 0.91 Zero-shot, greedy decoding Apr 2025 Official leaderboard
2 Qwen3-VL-8B-Instruct 0.89 Zero-shot, greedy decoding Oct 2025 Official leaderboard
3 Gemma 4 12B 0.88 Zero-shot, greedy decoding Jun 2026 Official leaderboard
4 Qwen3-VL-30B-A3B 0.86 Zero-shot, greedy decoding Official leaderboard
5 Qwen3-VL-32B-Instruct 0.83 Zero-shot, greedy decoding Oct 2025 Official leaderboard
6 InternVL3-8B 0.83 Zero-shot, greedy decoding Apr 2025 Official leaderboard
7 Molmo2-8B 0.82 Zero-shot, greedy decoding Dec 2025 Official leaderboard
8 InternVL3.5-8B 0.82 Zero-shot, greedy decoding Aug 2025 Official leaderboard
9 Gemma 3 12B 0.79 Zero-shot, greedy decoding Mar 2025 Official leaderboard
10 Qwen2.5-VL-7B 0.76 Zero-shot, greedy decoding Jan 2025 Official leaderboard
11 Phi-3.5-vision-instruct 0.75 Zero-shot, greedy decoding Aug 2024 Official leaderboard
12 InternVL3.5-38B 0.75 Zero-shot, greedy decoding Aug 2025 Official leaderboard
13 Pixtral 12B 0.69 Zero-shot, greedy decoding Sep 2024 Official leaderboard
14 llava-v1.6-vicuna-7b 0.66 Zero-shot, greedy decoding Jan 2024 Official leaderboard
15 Llama 3.2 11B 0.55 Zero-shot, greedy decoding Sep 2024 Official leaderboard
16 InternVL3.5-30B-A3B 0.49 Zero-shot, greedy decoding Aug 2025 Official leaderboard
17 Qwen2.5-VL-3B 0.42 Zero-shot, greedy decoding Jan 2025 Official leaderboard
18 llava-v1.6-mistral-7b 0.36 Zero-shot, greedy decoding Jan 2024 Official leaderboard
#ModelScoreSettingDateSource
1 InternVL3-38B 0.91 Zero-shot, greedy decoding Apr 2025 Official leaderboard
2 Qwen3-VL-8B-Instruct 0.89 Zero-shot, greedy decoding Oct 2025 Official leaderboard
3 Gemma 4 12B 0.88 Zero-shot, greedy decoding Jun 2026 Official leaderboard
4 Qwen3-VL-32B-Instruct 0.83 Zero-shot, greedy decoding Oct 2025 Official leaderboard
5 InternVL3-8B 0.83 Zero-shot, greedy decoding Apr 2025 Official leaderboard
6 Molmo2-8B 0.82 Zero-shot, greedy decoding Dec 2025 Official leaderboard
7 InternVL3.5-8B 0.82 Zero-shot, greedy decoding Aug 2025 Official leaderboard
8 Gemma 3 12B 0.79 Zero-shot, greedy decoding Mar 2025 Official leaderboard
9 Qwen2.5-VL-7B 0.76 Zero-shot, greedy decoding Jan 2025 Official leaderboard
10 Phi-3.5-vision-instruct 0.75 Zero-shot, greedy decoding Aug 2024 Official leaderboard
11 InternVL3.5-38B 0.75 Zero-shot, greedy decoding Aug 2025 Official leaderboard
12 Pixtral 12B 0.69 Zero-shot, greedy decoding Sep 2024 Official leaderboard
13 llava-v1.6-vicuna-7b 0.66 Zero-shot, greedy decoding Jan 2024 Official leaderboard
14 Llama 3.2 11B 0.55 Zero-shot, greedy decoding Sep 2024 Official leaderboard
15 InternVL3.5-30B-A3B 0.49 Zero-shot, greedy decoding Aug 2025 Official leaderboard
16 Qwen2.5-VL-3B 0.42 Zero-shot, greedy decoding Jan 2025 Official leaderboard
17 llava-v1.6-mistral-7b 0.36 Zero-shot, greedy decoding Jan 2024 Official leaderboard

Rankings by part

We read 22 parts from the benchmark’s own leaderboard in 4 groups: c1 taxonomy (exact match), c2 attributes (cags), c3 spatial and c4 re-id. Each ranks models on one part of the test. Qwen3-VL-32B-Instruct leads 12 of them, and 6 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

phylum

17 models we track have a score here.

  1. 1 InternVL3-38B 0.91
  2. 2 Qwen3-VL-8B-Instruct 0.89
  3. 3 Gemma 4 12B 0.88
  4. 4 Qwen3-VL-32B-Instruct 0.83
  5. 5 InternVL3-8B 0.83
  6. 6 Molmo2-8B 0.82
  7. 7 InternVL3.5-8B 0.82
  8. 8 Gemma 3 12B 0.79
  9. 9 Qwen2.5-VL-7B 0.76
  10. 10 Phi-3.5-vision-instruct 0.75

Number one over time

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

Shanghai AI Lab
Own leaderboard Not tested since Aug 2026

Source: Official Bio-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
0.40 0.60 0.80 1.00 2024 2025 2026 0.40 0.60 0.80 1.00 2024 2025 2026

Source: Official Bio-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 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 official leaderboard (18 entries).
  • Pass Models scored 17 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from June 2026, for Gemma 4 12B.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on smrayeed.github.io: 17 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