Benchmark Almanac

LHRS-Bench

GPT-4-Turbo (snapshot unspecified) 44.6% tops its leaderboard Claude 3 Opus 39.1% leads the models we track
Not in model cards

Models answer 690 single-choice questions about 108 remote sensing images. The questions cover land use, object locations, image resolution, and other properties.

TerraAgent reported 46.30% average accuracy across eleven capabilities. The authors described the questions in March 2024 and released the files in July 2024.

Released
March 2024
Kind
General visual questions
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, Maps and geodata → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
Claude 3 Opus #173 on the capability index
Last model added
February 2024
Scores refreshed
November 20th, 2026
9
Entries in its paper, 3 models we track

GPT-4-Turbo (snapshot unspecified) tops the leaderboard with 44.6% Claude 3 Opus leads with 39.1% among models released by February 2024

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Claude 3 Opus, at 39.1%. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2024, 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-4-Turbo (snapshot unspecified) 44.6%
  2. 2 LHRS-Bot 39.4%
  3. 3 Claude 3 Opus 39.1%
  4. 4 LLaVA-1.5 37.5%
  5. 5 mPLUG-Owl2 37%
  6. 6 InternLM-XComposer 31.1%
  7. 7 Qwen-VL-Chat 28.6%
  8. 8 InstructBLIP 18.9%
  9. 9 MiniGPTv2 16.9%

Source: The LHRS-Bench paper

Source: The LHRS-Bench paper

#EntryScoreSettingDateSource
1 GPT-4-Turbo (snapshot unspecified) 44.6% Official leaderboard
2 LHRS-Bot 39.4% Official leaderboard
3 Claude 3 Opus 39.1% Feb 2024 Official leaderboard
4 LLaVA-1.5 37.5% Official leaderboard
5 mPLUG-Owl2 37% Nov 2023 Official leaderboard
6 InternLM-XComposer 31.1% Official leaderboard
7 Qwen-VL-Chat 28.6% Aug 2023 Official leaderboard
8 InstructBLIP 18.9% Official leaderboard
9 MiniGPTv2 16.9% Official leaderboard
#ModelScoreSettingDateSource
1 Claude 3 Opus 39.1% Feb 2024 Official leaderboard
2 mPLUG-Owl2 37% Nov 2023 Official leaderboard
3 Qwen-VL-Chat 28.6% Aug 2023 Official leaderboard

Rankings by part

We read 11 parts from the benchmark’s paper, each ranking models on one part of the test, such as Identity, Color and Orientation. Claude 3 Opus leads 7 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Identity

3 models we track have a score here.

  1. 1 mPLUG-Owl2 ↑1 41.5%
  2. 2 Claude 3 Opus ↓1 41%
  3. 3 Qwen-VL-Chat 31.4%

Number one over time

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

Anthropic
Benchmark paper Not tested since Mar 2024

Source: The LHRS-Bench paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Claude 3 Opus mPLUG-Owl2 Qwen-VL-Chat 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Claude 3 Opus Qwen-VL-Chat

Source: Official LHRS-Bench 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in February 2024, for Claude 3 Opus. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 3 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Claude 3 Opus.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude 3 Opus (#173).
  • Pass Headroom The best is 39.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 3 rows for models we track and 6 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