Benchmark Almanac

CURIE Geospatial Dataset Extraction

Gemini 2.0 Flash Feb 2025 29.7 leads since February 2025
Not in model cards

Models read a research paper and list its datasets, variables, sources, time spans, and geographic coverage in JSON. The authors report ROUGE-L and BERTScore.

Google reports scores for nine models on 19 papers. The released archive contains a matching answer file for each paper.

Kind
Finding facts in long inputs
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Documents → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 2.0 Flash Feb 2025 #147 on the capability index
Last model added
February 2025
Scores refreshed
November 21st, 2026
9
Entries in its paper, 4 models we track

Gemini 2.0 Flash leads with 29.7 among models released by February 2025 Gemini 2.0 Flash leads with 29.7 among models released by February 2025

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The GEO task reports no combined score, so this headline uses its ROUGE-L column. 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 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 Gemini 2.0 Flash Feb 2025 29.7
  2. 2 Claude 3 Opus 28.7
  3. 3 Gemini 1.5 Flash (snapshot unspecified) 27.8
  4. 4 GPT-4o (snapshot unspecified) 27.3
  5. 5 Gemini 1.5 Pro (snapshot unspecified) 27.2
  6. 6 Gemini 1.0 Pro 22.6
  7. 7 Command R+ 21.4
  8. 8 Mixtral 20.2
  9. 9 LongLLaMa 9.53

Source: The CURIE Geospatial Dataset Extraction paper

#EntryScoreSettingDateSource
1 Gemini 2.0 Flash Feb 2025 29.7 Feb 2025 Official leaderboard
2 Claude 3 Opus 28.7 Feb 2024 Official leaderboard
3 Gemini 1.5 Flash (snapshot unspecified) 27.8 Official leaderboard
4 GPT-4o (snapshot unspecified) 27.3 Official leaderboard
5 Gemini 1.5 Pro (snapshot unspecified) 27.2 Official leaderboard
6 Gemini 1.0 Pro 22.6 Dec 2023 Official leaderboard
7 Command R+ 21.4 Aug 2024 Official leaderboard
8 Mixtral 20.2 Official leaderboard
9 LongLLaMa 9.53 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 2.0 Flash Feb 2025 29.7 Feb 2025 Official leaderboard
2 Claude 3 Opus 28.7 Feb 2024 Official leaderboard
3 Gemini 1.0 Pro 22.6 Dec 2023 Official leaderboard
4 Command R+ 21.4 Aug 2024 Official leaderboard

3 models have held number one in the benchmark’s paper since 2023

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

Google DeepMind Anthropic
Benchmark paper Not tested since Feb 2025

Source: The CURIE Geospatial Dataset Extraction 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
20.0 22.0 24.0 26.0 28.0 30.0 2024 2025 20.0 22.0 24.0 26.0 28.0 30.0 2024 2025

Source: Official CURIE Geospatial Dataset Extraction 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 Long context

All 115 in Long context
  • MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens. Muse Spark 1.3 98.5%
  • LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy. Inkling 2 Small 70.6%
  • GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
  • OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin. Gemini 3.7 Flash 89%
  • CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
  • AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key. Step 5 Preview 88.3%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 21 months ago, in February 2025, for Gemini 2.0 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 benchmark’s paper (9 entries).
  • Pass Models scored 4 models we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 21 months ago, in February 2025, for Gemini 2.0 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.0 Flash (#147).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 4 rows for models we track and 5 other entries at the last read.
  • Pass Last read November 21st, 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