Benchmark Almanac

INQUIRE-Fullrank

CLIP ViT-H/14-378 (DFN) + GPT-4o 47.1% tops its leaderboard
Not in model cards
Version Fullrank

Models retrieve wildlife photographs from five million iNaturalist images for ecological queries. The benchmark measures average precision among the first 50 results.

The organizers list 18 scored model configurations plus a random baseline. The release has 200 test queries and 50 validation queries.

Made by
INQUIRE team
Released
June 2024
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
Run by
Anyone
18
Entries on its own leaderboard, 0 models we track

CLIP ViT-H/14-378 (DFN) + GPT-4o tops the leaderboard with 47.1%

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.

  1. 1 CLIP ViT-H/14-378 (DFN) + GPT-4o 47.1%
  2. 2 CLIP ViT-H/14-378 (DFN) + VILA1.5-40B 42.1%
  3. 3 CLIP ViT-H/14-378 (DFN) + GPT-4-Turbo (20240409) 38.8%
  4. 4 CLIP ViT-H/14-378 (DFN) + PaliGemma-3B-mix-448 37.7%
  5. 5 CLIP ViT-H/14-378 (DFN) + LLaVA-v1.6-34B 37.4%
  6. 6 CLIP ViT-H/14-378 (DFN) 35.6%
  7. 7 SigLIP SO400m-14-384 34.9%
  8. 8 SigLIP ViT-L/16-384 31.6%
  9. 9 CLIP ViT-L/14 (DFN) 24.6%
  10. 10 CLIP ViT-B/16 (DFN) 16.2%
  11. 11 CLIP ViT-L/14 (OpenAI) 15.8%
  12. 12 CLIP RN50x16 (OpenAI) 14.3%
  13. 13 CLIP ViT-B/16 (OpenAI) 11.4%
  14. 14 CLIP ViT-B/32 (OpenAI) 8.20%
  15. 15 CLIP RN50 (OpenAI) 7.60%
  16. 16 WildCLIP-t1 7.50%
  17. 17 WildCLIP-t1t7-lwf 7.30%
  18. 18 BioCLIP 3.60%

Source: Official INQUIRE-Fullrank leaderboard

#EntryScoreSettingDateSource
1 CLIP ViT-H/14-378 (DFN) + GPT-4o 47.1% Official leaderboard
2 CLIP ViT-H/14-378 (DFN) + VILA1.5-40B 42.1% Official leaderboard
3 CLIP ViT-H/14-378 (DFN) + GPT-4-Turbo (20240409) 38.8% Official leaderboard
4 CLIP ViT-H/14-378 (DFN) + PaliGemma-3B-mix-448 37.7% Official leaderboard
5 CLIP ViT-H/14-378 (DFN) + LLaVA-v1.6-34B 37.4% Official leaderboard
6 CLIP ViT-H/14-378 (DFN) 1B 35.6% Official leaderboard
7 SigLIP SO400m-14-384 0.9B 34.9% Official leaderboard
8 SigLIP ViT-L/16-384 0.7B 31.6% Official leaderboard
9 CLIP ViT-L/14 (DFN) 0.4B 24.6% Official leaderboard
10 CLIP ViT-B/16 (DFN) 0.2B 16.2% Official leaderboard
11 CLIP ViT-L/14 (OpenAI) 0.4B 15.8% Official leaderboard
12 CLIP RN50x16 (OpenAI) 0.3B 14.3% Official leaderboard
13 CLIP ViT-B/16 (OpenAI) 0.2B 11.4% Official leaderboard
14 CLIP ViT-B/32 (OpenAI) 0.1B 8.20% Official leaderboard
15 CLIP RN50 (OpenAI) 0.1B 7.60% Official leaderboard
16 WildCLIP-t1 0.2B 7.50% Official leaderboard
17 WildCLIP-t1t7-lwf 0.2B 7.30% Official leaderboard
18 BioCLIP 0.2B 3.60% Official 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.

Versions

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 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 (18 entries).
  • Pass Models scored 18 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on inquire-benchmark.github.io: 18 entries at the last read, none a model we track.
  • 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