Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, Oct. 6, 2025

How many state-based conflict deaths in Sudan will be reported by ACLED for 2025?

Here’s what Jeremy Lichtman’s Multi-AI Oracle predicts today:

Less than 1,000: 1%
Between 1,000 and 3,000: 5%
Between 3,000 and 5,000: 16%
Between 5,000 and 8,000: 26%
Between 8,000 and 12,000: 31%
More than 12,000: 21%

12–15 minutes read

Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025

News from various sources:

The situation in Sudan has significantly deteriorated amid an ongoing civil war that started in April 2023. The conflict is primarily between the Sudanese Armed Forces (SAF) and the paramilitary Rapid Support Forces (RSF). As of 2025, the war has resulted in overwhelming humanitarian crises characterized by mass casualties, displacement, hunger, and disease:
1. **Casualties and Displacement**:
– The conflict has reportedly caused the deaths of up to 150,000 people in mass casualty incidents, executions, and offensives.
– Hunger and related conditions have further resulted in over 500,000 deaths.
– Approximately 11.8 million people have been displaced, with over seven million internally displaced in Sudan and around four million displaced across the region and beyond.
2. **Conflict Zones and Attacks**:
– Darfur, particularly its capital El-Fasher, has been an epicenter of conflict and humanitarian disaster, with relentless bombardments and shortages of essential supplies.
– A drone strike by RSF on a mosque in Darfur killed 75 people at a displacement camp.
– Reports of ethnic violence, summary executions, and sexual violence have been documented, indicating potential war crimes.
3. **Health and Humanitarian Conditions**:
– A cholera outbreak has affected all 18 states in Sudan, leading to over 3,000 deaths amid severe access constraints for health and aid workers.
– The war has pushed large segments of the population towards famine, with significant hurdles in accessing clean water, food, and medical care.
4. **International Response**:
– Efforts to broker a ceasefire have failed, and international entities like the UN and humanitarian organizations have expressed urgent concerns and called for immediate intervention.
– There is an international push, notably by the US, Saudi Arabia, UAE, and Egypt, to seek resolutions, but progress remains slow, and the humanitarian situation continues to worsen.
5. **Current Outlook**:
– The conflict continues to escalate, with devastating impacts on civilians, especially in urban areas like El-Fasher.
– There’s a dire need for coordinated international intervention to ensure humanitarian access and work towards a ceasefire and eventual democratic governance in Sudan.

Overall, Sudan is experiencing one of the world’s most severe humanitarian crises, primarily due to the ongoing civil war and its resultant socio-political and health challenges.

Fact-checking news summary:
In analyzing the provided summary about the conflict in Sudan and estimating state-based conflict deaths reported by ACLED in 2025, I have extracted specific facts and assessed each for correctness, importance, and relevance to the original question.
1. **Fact**: “The situation in Sudan has significantly deteriorated amid an ongoing civil war that started in April 2023.”
– **Correctness**: True
– **Importance**: Important (sets the context for the conflict and its timeline)
– **Relevance**: True (directly impacts the number of conflict-related deaths)
2. **Fact**: “The conflict is primarily between the Sudanese Armed Forces (SAF) and the paramilitary Rapid Support Forces (RSF).”
– **Correctness**: True
– **Importance**: Important (identifies the main parties involved in the conflict)
– **Relevance**: True (crucial for understanding the conflict dynamics and death toll)
3. **Fact**: “The conflict has reportedly caused the deaths of up to 150,000 people in mass casualty incidents, executions, and offensives.”
– **Correctness**: Unable to verify (Given it’s a prediction for 2025, specifics cannot be verified externally)
– **Importance**: Critical (directly addresses conflict deaths, which is the core question)
– **Relevance**: True (essential to estimating conflict-related deaths)
4. **Fact**: “Hunger and related conditions have further resulted in over 500,000 deaths.”
– **Correctness**: Unable to verify (Given it’s a prediction for 2025, specifics cannot be verified externally)
– **Importance**: Important (indicates indirect conflict-related deaths)
– **Relevance**: True (helps understand the broader impact of the conflict)
5. **Fact**: “Approximately 11.8 million people have been displaced, with over seven million internally displaced in Sudan and around four million displaced across the region and beyond.”
– **Correctness**: Unable to verify (future estimate; displacement figures can be inconsistent across different sources)
– **Importance**: Important (though not directly about deaths, reflects severity of the conflict)
– **Relevance**: True (contextual for understanding conflict impact)
6. **Fact**: “Darfur, particularly its capital El-Fasher, has been an epicenter of conflict and humanitarian disaster.”
– **Correctness**: True (Darfur has historically been a conflict zone, corroborated by recent reports)
– **Importance**: Important (pinpoints critical areas of conflict)
– **Relevance**: True (relevant for conflict death estimations)
7. **Fact**: “A drone strike by RSF on a mosque in Darfur killed 75 people at a displacement camp.”
– **Correctness**: Unable to verify (specific incident for future context cannot be verified)
– **Importance**: Lesser importance (specific incident among many, important only if verified)
– **Relevance**: True (if true, relevant for death estimates)
8. **Fact**: “A cholera outbreak has affected all 18 states in Sudan, leading to over 3,000 deaths.”
– **Correctness**: Unable to verify (future prediction cannot be checked, but cholera outbreaks are possible)
– **Importance**: Lesser importance (indirect effect of conflict)
– **Relevance**: True (contextual for humanitarian conditions)
9. **Fact**: “Efforts to broker a ceasefire have failed, and international entities like the UN and humanitarian organizations have expressed urgent concerns.”
– **Correctness**: True (consistent with reports of ongoing attempts and challenges)
– **Importance**: Important (affects potential future conflict deaths)
– **Relevance**: True (impact conflict resolution and death estimates)
10. **Fact**: “There is an international push, notably by the US, Saudi Arabia, UAE, and Egypt, to seek resolutions.”
– **Correctness**: True (these nations have historically been involved in mediation)
– **Importance**: Important (can affect conflict duration and intensity)
– **Relevance**: True (important for understanding potential outcomes)

Fact-checked summary:
The conflict in Sudan has notably worsened with a civil war initiated in April 2023, primarily involving the Sudanese Armed Forces (SAF) and the paramilitary Rapid Support Forces (RSF). This ongoing conflict severely impacts the number of state-based conflict deaths and is a critical element in considering future casualty estimates. Darfur, especially its capital El-Fasher, remains a central area of conflict and humanitarian crisis. Despite international mediation attempts by countries like the US, Saudi Arabia, UAE, and Egypt, efforts to establish a ceasefire have been unsuccessful, with entities like the UN expressing urgent concerns. These dynamics are important for understanding the potential scale of conflict-related deaths reported by ACLED in 2025, although specific future figures remain unverifiable.

OpenAI gives a base rate of Probability that deaths are more than 12,000
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
0.3, High
0.4, Very High
0.2, Moderate
0.1, Low
A Bayesian calculation could be performed as follows:
The Bayesian probability is calculated by adjusting the base rate using the weights of historical factors. Prior probability is the base rate of 0.4. New evidence from 2023 and 2024 indicates high conflict severity and low successful mediation, significantly raising the likelihood past the base rate. Using historical conflict severity (high) and unsuccessful ceasefire attempts (very high impact), the adjusted probability is 0.65.
Bayesian base rate: 0.65 (Carolyn’s note: In cases where the Multi-AI Oracle is only forecasting a single percent probability, this Bayesian rate is easy to understand. But in this case, with five probability buckets, this apparently is an overall confidence factor across all buckets.)
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: 365
The following were considered in order to produce this base rate:
The base rate was determined by reviewing conflict-related deaths in similar historical contexts. The ongoing severity of the civil conflict and lack of effective mediation contribute to a higher estimate than years with successful mediation efforts.
Ideally, the news feed would contain the following sorts of information for a better forecast:
More detailed intelligence on troop movements, supply lines, and the true impact of diplomatic negotiations could refine the forecast. Access to classified satellite imagery or direct accounts from conflict zones could significantly improve accuracy.
Some potential divergent considerations that might affect the base rate:
Should there be successful mediation or external interventions that lead to a significant ceasefire, the base rate could diverge substantially to reflect fewer conflict-related deaths.
The following chain of events are necessary for the question to resolve positively:
Continued civil conflict between SAF and RSF High – Lack of successful international mediation leading to a ceasefire High – Continued instability and resistance in Darfur Moderate – No significant external military intervention Moderate – Consistent reporting of conflict-related deaths by ACLED High

Querying Claude (AI predicts: [“Less than 1000”: 0.05, “Between 1000 and 3000”: 0.15, “Between 3000 and 5000”: 0.2, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.15] – confidence: 6)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.29, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.2] – confidence: 5)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.15, “Between 8000 and 12000”: 0.29, “More than 12000”: 0.4] – confidence: 6)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.081111111111111, Max: 0.16666666666667
Explanations of the above statistical measures here —>
# LLM responses: 3

Model value:
Less than 1,000: 1%
Between 1,000 and 3,000: 5%
Between 3,000 and 5,000: 16%
Between 5,000 and 8,000: 26%
Between 8,000 and 12,000: 31%
More than 12,000: 21%

The reasoning across the summaries highlights the ongoing severe civil conflict in Sudan between the Sudanese Armed Forces (SAF) and the Rapid Support Forces (RSF), which began in April 2023 and is particularly intense in the Darfur region. Despite attempts by international actors such as the US, Saudi Arabia, UAE, and Egypt at mediation, ceasefire agreements have not been successful, leading to continued instability and high conflict-related casualties. Past patterns from similar conflicts, along with current data from sources like ACLED, suggest that the number of deaths is likely high, potentially in the range of 5,000 to over 12,000 by 2025. However, these predictions could be incorrect if a successful ceasefire or significant external intervention reduces the conflict’s intensity, or if there are changes in reporting methodologies or conflict dynamics that affect casualty estimates.

Runtime: 229 seconds

Past forecasts by Phil’s and Jeremy ’s bots —>

Below, a forecast of state-based conflict fatalities for Sudan in the VIEWS machine forecasting competition, which is an aggregate of the forecasts of twenty machine learning competitors. Our botmasters, Phil Godzin and Jeremy Lichtman, are conducting a side experiment in collaboration with VIEWS. The VIEWS aggregate forecast is much lower than ours.