ClimateCheck 2025
Version 2025
Models retrieve ten scientific abstracts for a climate claim. They label whether each abstract supports the claim, refutes it, or provides too little evidence.
Three teams submitted verification results using Gemini 2.5, GPT-4.1 and Qwen 14B. The organizers scored retrieval and verification separately.
- Released
- February 2025
- Kind
- Faithful to sources
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Earth and environmental sciences
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- Anyone
Gemini 2.5 Pro (snapshot unspecified) tops the leaderboard with 1.39 No scores yet
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 ranks claim verification by the sum of F1 and retrieval Recall@10. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as akiepura_jlam pipeline + GPT-4.1, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
- 1 Gemini 2.5 Pro (snapshot unspecified) Zero-shot with distribution guidelines 1.39
- 2 akiepura_jlam pipeline + GPT-4.1 Hybrid zero-shot 1.30
- 3 EFC pipeline + Qwen3-14B Zero-shot with reasoning 1.29
- 4 Yi-1.5-9B-Chat-16K Zero-shot 0.98
Source: The ClimateCheck 2025 paper
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Gemini 2.5 Pro (snapshot unspecified) | 1.39 | Zero-shot with distribution guidelines, Ant Bridge pipeline | Ant Bridge | Official leaderboard | |
| 2 | akiepura_jlam pipeline + GPT-4.1 | 1.30 | Hybrid zero-shot | akiepura_jlam | Apr 2025 | Official leaderboard |
| 3 | EFC pipeline + Qwen3-14B | 1.29 | Zero-shot with reasoning | EFC | Apr 2025 | Official leaderboard |
| 4 | Yi-1.5-9B-Chat-16K | 0.98 | Zero-shot, Our baseline pipeline | Our baseline | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|
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 Factuality
- SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references.
Qwen3.7-Plus 81.7%
- HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy.
Keye-VL-2.0-30B-A3B 73.5%
- SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge.
Gemini 3.1 Pro 77.5%
- AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones.
Inkling 2 Small 16.1
- GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages.
Amazon Nova Pro 60.7%
- Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. GPT-6 Astra 4.20%
Data audit
All 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (4 entries).
- Note Models scored 4 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 2 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.