Benchmark Almanac

RQA-70K weather radar forecast evaluation

RadarQA 61.5% tops its leaderboard o1 52.7% leads the models we track
Not in model cards

Models compare forecast radar images or sequences with observations. They rate errors such as missed storms and false alarms and write assessments of forecast quality.

The Omni-Weather paper ran the four RadarQA tasks and reported results for GPT-5 and Claude Sonnet 4. Rating accuracy and written assessment scores use different scales.

Released
August 2025
Kind
Lab and data work
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Time series, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
o1 #118 on the capability index
Last model added
February 2025
Scores refreshed
November 20th, 2026
8
Entries in its paper, 5 models we track

RadarQA tops the leaderboard with 61.5% o1 leads with 52.7% among models released by February 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports separate rating and assessment metrics. The headline is overall frame-rating accuracy from Table 2. 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 o1, at 52.7%. This view shows only models we track, each at its best.

The newest model with a score here came out in February 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 RadarQA 61.5%
  2. 2 o1 52.7%
  3. 3 GPT4o (snapshot unspecified) 48.8%
  4. 4 Claude 3.7 Sonnet 39.8%
  5. 5 InternVL2.5-8B 30.9%
  6. 6 Qwen2.5-VL-72B 23.8%
  7. 7 Gemini2.5 pro (snapshot unspecified) 21.4%
  8. 8 Qwen2.5-VL-7B 20.1%

Source: The RQA-70K weather radar forecast evaluation paper

Source: The RQA-70K weather radar forecast evaluation paper

#EntryScoreSettingDateSource
1 RadarQA 61.5% Official leaderboard
2 o1 52.7% Dec 2024 Official leaderboard
3 GPT4o (snapshot unspecified) 48.8% Official leaderboard
4 Claude 3.7 Sonnet 39.8% Feb 2025 Official leaderboard
5 InternVL2.5-8B 30.9% Dec 2024 Official leaderboard
6 Qwen2.5-VL-72B 23.8% Jan 2025 Official leaderboard
7 Gemini2.5 pro (snapshot unspecified) 21.4% Official leaderboard
8 Qwen2.5-VL-7B 20.1% Jan 2025 Official leaderboard
#ModelScoreSettingDateSource
1 o1 52.7% Dec 2024 Official leaderboard
2 Claude 3.7 Sonnet 39.8% Feb 2025 Official leaderboard
3 InternVL2.5-8B 30.9% Dec 2024 Official leaderboard
4 Qwen2.5-VL-72B 23.8% Jan 2025 Official leaderboard
5 Qwen2.5-VL-7B 20.1% Jan 2025 Official leaderboard

Number one over time

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

OpenAI
Benchmark paper Not tested since Aug 2025
o1 52.7%

Source: The RQA-70K weather radar forecast evaluation 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% 2025 Near the ceiling (85%) o1 InternVL2.5-8B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o1 InternVL2.5-8B

Source: Official RQA-70K weather radar forecast evaluation 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 21 months ago, in February 2025, for Claude 3.7 Sonnet. 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 (8 entries).
  • Pass Models scored 5 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 21 months ago, in February 2025, for Claude 3.7 Sonnet.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o1 (#118).
  • Pass Headroom The best is 52.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 5 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