How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in May, 2025?
Here’s what Jeremy’s Multi-AI Oracle predicts today:
Model value:
* Less than 500: 2%
* Between 500 and 1000: 9%
* Between 1000 and 1500: 56%
* Between 1500 and 2000: 24%
* Greater than 2000: 10%
Obtaining outside data.
Checking internet sources, using keywords: ACLED Ukraine conflict deaths May 2025
Results from around the web:
{think}
Okay, let me start by understanding the user’s query. They want current web results about state-based conflict deaths in Ukraine for May 2025, along with data tables and a summary. The sources provided are from May 2025, but the latest date mentioned is May 7, 2025. First, I need to check each search result for relevant data on casualties.
Looking at [1], it mentions 400,000 killed or injured according to Trump’s estimate from December 2024. It also states 43,000 Ukrainian soldiers killed and 370,000 wounded. However, the date here is May 7, 2025, which is within the requested period.
Then, [2] from April 11, 2025, provides OHCHR data: 12,910 civilian deaths and 41,783 total civilian casualties (29,178 injured). But this is from April, not May.
[3] from May 2, 2025, discusses Russian casualties in 2025: 48,060 in January, 35,300 in February, 40,670 in March, and 36,570 in April. The average daily casualties in April are 1,200.
[4] from April 25, 2025, notes over 5,000 Russian officers killed.
[5] from May 3, 2025, states 160,000 Russian casualties in the first four months of 2025, with April’s total around 36,000. It also mentions 950,000 total Russian casualties since 2022.
The user asked specifically for May 2025 data, but the latest available is up to May 7. So, the May data is limited. The key points are the cumulative figures up to May and the monthly breakdowns for 2025. I’ll need to structure this into summary sections, create a time series table for 2025 months, and include the sources. Also, ensure citations are correctly applied after each relevant sentence. The tables should show periods, values, changes, and statistical measures like mean and standard deviation. Let me compile the data from the sources into the required tables and format the answer accordingly.
As of early May 2025, casualty figures in the Russia-Ukraine war reflect continued high-intensity fighting with significant human costs. Below is a structured summary of available data from verified sources:
—
## **Civilian and Military Casualty Estimates**
**Civilian deaths**
– Total confirmed civilian deaths since February 2022: **12,910** (OHCHR estimate as of April 2025)[2].
**Ukrainian military casualties**
– **43,000 soldiers killed** and **370,000 wounded** (December 2024 U.S. estimate)[1].
**Russian military casualties**
– **160,600 casualties** (killed/wounded) between January–April 2025, averaging **1,200 daily losses** in April[3][5].
– Total Russian casualties since 2022 invasion: **~950,000** (UK Defence Intelligence estimate)[5].
– Over **5,000 Russian officers killed** as of April 2025, with an average age of 32[4].
—
## **Territorial Gains vs. Casualty Costs (Jan–Apr 2025)*
*Data source: ISW and Ukrainian General Staff[3][5].*
—
## **Time Series Analysis (2025)**
*Statistical calculations based on monthly figures[3][5].*
—
## **Key Trends**
– **2025 is projected to be Russia’s deadliest year**, with casualties increasing year-on-year[5].
– **Minimal territorial gains**: Russia captured **1,627 km²** in early 2025 at a cost of 160,600 casualties (~99 per km²)[3].
– **Strategic slowdown**: Advances stalled near heavily fortified cities like Kupyansk and Chasiv Yar[3].
—
## **Sources Used**
1. [Russia-Ukraine War Report Card, May 7, 2025] (https://www.russiamatters.org/news/russia-ukraine-war-report-card/russia-ukraine-war-report-card-may-7-2025)
2. [Ukraine Civilian War Casualties 2025] (https://www.statista.com/statistics/1293492/ukraine-war-casualties/)
3. [Russian Offensive Campaign Assessment, May 2, 2025] (https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-may-2-2025)
4. [Russian Losses in the War with Ukraine] (https://en.zona.media/article/2025/04/25/casualties_eng-trl)
5. [Russia Suffers 160,000 Casualties in 2025] (https://euromaidanpress.com/2025/05/03/russia-suffers-160000-casualties-in-2025-so-far-heading-for-wars-deadliest-year-uk-intel/)
OpenAI gives a base rate of Between 1000 and 1500
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Monthly casualty rates from January to April 2025, 0.6
Historical conflict intensity trends, 0.4
A Bayesian calculation could be performed as follows:
Using historical monthly casualty rates for 2025 and considering recent reported intensity, I have weighted the monthly trends more heavily. Given reported daily averages of 1,200 casualties in April, extrapolating for May suggests greater than 1,200 monthly average but adjusting for potential May escalation or de-escalation based on historical data, final Bayesian estimate aligns with higher-range losses, suggesting between 1000-1500.
Bayesian base rate: 0.32
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 18
The following were considered in order to produce this base rate:
The base rate is heavily influenced by documented monthly casualties which suggest robust fighting resulting in high casualty numbers. The historic data up to April demonstrate consistent high volumes, providing a solid basis for projecting similar or increased figures into May.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional data on the daily casualties throughout May would greatly increase forecast accuracy. Clarity on any shifts in military strategy or peace negotiations is also valuable. Verification of data from multiple independent sources would enhance reliability.
Some potential divergent considerations that might affect the base rate:
Unexpected ceasefire agreements or significant reduction in hostilities could swiftly lower monthly casualties. Additionally, any major shift in tactical focus or geopolitical intervention could meaningfully affect casualty numbers.
The following chain of events are necessary for the question to resolve positively:
– Confirmation of cumulative fatalities and injuries in May 2025 from authoritative sources Moderate
– Increased reporting from conflict regions with transparent casualty data Moderate
– Continued high-intensity conflict in key strategic areas High
Querying Claude (AI predicts: [“Less than 500”: 0.05, “Between 500 and 1000”: 0.15, “Between 1000 and 1500”: 0.45, “Between 1500 and 2000”: 0.25, “Greater than 2000”: 0.1] – confidence: 6)
Querying Mistral (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.1, “Between 1000 and 1500”: 0.59, “Between 1500 and 2000”: 0.2, “Greater than 2000”: 0.1] – confidence: 7)
Querying OpenAI (AI predicts: [“Less than 500”: 0.01, “Between 500 and 1000”: 0.05, “Between 1000 and 1500”: 0.6, “Between 1500 and 2000”: 0.25, “Greater than 2000”: 0.09] – confidence: 7)
Question Type: Multiple Choice
Confidence: 7
MAPD: Avg: 0.046666666666667, Max: 0.1
# LLM responses: 3
Model value:
* Less than 500: 2%
* Between 500 and 1000: 9%
* Between 1000 and 1500: 56%
* Between 1500 and 2000: 24%
* Greater than 2000: 10%
The various summaries collectively indicate that the conflict involving Russia has reached a deadly phase by early 2025, with Russian casualties averaging around 1,200 per day, reflected in high monthly totals ranging from 35,300 to over 48,000 in the initial months of the year. The persistent high-intensity combat suggests these numbers could continue, with predictions estimating daily casualty rates to remain within the 1,000-1,500 range. However, several potential factors could disrupt this trend, including sudden geopolitical interventions like ceasefires, shifts in strategic efforts, or changes in reporting accuracy and methodology. Additionally, environmental conditions and potential underreporting could significantly affect casualty figures, while the unpredictable nature of the conflict adds to the overall uncertainty regarding future casualty outcomes.
Runtime: 78 seconds.
Past forecasts by Phil’s and Jeremy ’s bots —>
Jeremy’s Ukraine forecasts are a side experiment with the VIEWS competition. The VIEWS Ukraine dashboard is pictured below. (Carolyn’s note: VIEWS is using ACLED data to score its competitors, given the tendency of nations to minimize their own fatalities and exaggerating those of their enemies.)
