Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, Oct. 20, 2025

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

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%

11–14 minutes read

Obtaining outside data.
Checking internet sources, using keywords: Sudan state-based conflict 2025
News from various sources:

The “Sudan state-based conflict 2025” content provides a comprehensive overview of the ongoing civil war in Sudan, focusing on its regional implications, international responses, and humanitarian impact. Below is a summarized breakdown of the key points:
1. **International Mediation Efforts**: In September 2025, Egypt, Saudi Arabia, the UAE, and the United States announced a “Quad” initiative for a road map aimed at ending Sudan’s civil war, which began in April 2023. This plan, which called for a humanitarian truce and a political transition to a civilian-led government, has faced challenges, with the Sudan Armed Forces (SAF) rejecting the proposal, leading to continued fighting.
2. **Regional and Global Dynamics**:
– The conflict is deeply entangled with regional rivalries. Egypt supports SAF, while the UAE backs the Rapid Support Forces (RSF). The war reflects a broader pattern where regional powers like the UAE and Turkey are increasingly involving themselves in Africa’s geopolitics, often complicating mediation efforts.
– The U.S.’s influence in the Horn of Africa has waned, leading to complications in mediation efforts, as regional middle powers now play a significant role.
3. **Humanitarian Concerns**:
– The war has displaced millions and severely impacted Sudan’s infrastructure, critical services, and the civilian population, with widespread reports of atrocities, including alleged use of chemical weapons by the SAF.
– In South Sudan, local communities struggle to integrate over one million refugees, facing challenges like healthcare shortages and infrastructure strain.
4. **Impact on Religious Minorities**:
– Sudan’s Christian minority, around 4% of the population, has suffered severe persecution and discrimination in the ongoing conflict, facing food shortages and targeted attacks from both warring factions.
5. **International Justice and Accountability**:
– The International Criminal Court (ICC) convicted Ali Kosheib, a former Janjaweed militia leader, for crimes committed in Darfur during the early 2000s. This landmark conviction highlights the ongoing struggle for accountability in Sudan, with both the SAF and RSF accused of fresh war crimes in the current conflict.
6. **Calls for Comprehensive Peace Solutions**:
– Egyptian Foreign Minister Badr Abdelatty stressed the need for a Sudanese-led peace process and global governance reforms to ensure fairer representation for developing nations. This includes emphasizing ownership in the peace process and rejecting external interference.
7. **Human Rights Organizations’ Role**:
– Organizations like Human Rights Watch continue to document war crimes and urge international bodies to prosecute violations, advocating for expanded ICC jurisdiction beyond Darfur to address crimes committed across Sudan since April 2023.

The complexity of Sudan’s conflict, entrenched regional interests, and humanitarian crises highlight the difficulties in achieving peace, underscoring the need for coordinated international action and support for justice and accountability initiatives.

Fact-checking news summary:
Based on the provided summary, here is a list of specific facts, with an evaluation of their correctness, importance to the resolution of the question, and relevance:
1. **International Mediation Efforts**: In September 2025, Egypt, Saudi Arabia, the UAE, and the United States announced a “Quad” initiative for a road map aimed at ending Sudan’s civil war, which began in April 2023. The SAF rejected the proposal, continuing the fighting.
– Correct: Cannot verify specifics for 2025, but the actors and context are plausible as of current knowledge.
– Importance: Lesser (does not directly address the number of deaths).
– Relevance: True.
2. **Regional and Global Dynamics**: Egypt supports SAF, while the UAE backs the RSF. The conflict reflects regional rivalries, complicating mediation.
– Correct: Plausible based on known regional allegiances, but not specific to 2025.
– Importance: Lesser.
– Relevance: True.
3. **U.S.’s influence in the Horn of Africa has waned, complicating mediation efforts.**
– Correct: Plausible based on recent trends but not specific to 2025.
– Importance: Unimportant.
– Relevance: False.
4. **Humanitarian Concerns**: The war has displaced millions, severely impacting Sudan’s infrastructure, services, and civilian population, with reports of atrocities and alleged chemical weapons use by the SAF.
– Correct: Consistent with expected consequences of civil war, but specifics for 2025 can’t be confirmed.
– Importance: Important (impacts death toll indirectly).
– Relevance: True.
5. **South Sudan faces challenges integrating over one million refugees.**
– Correct: Cannot verify specific number of refugees, plausible but not specific to 2025.
– Importance: Lesser.
– Relevance: True.
6. **Impact on Religious Minorities**: Sudan’s Christian minority, around 4% of the population, faces persecution and shortages.
– Correct: Consistent with ongoing persecution reports, but specific details for 2025 unconfirmed.
– Importance: Lesser.
– Relevance: False.
7. **International Justice and Accountability**: The ICC convicted Ali Kosheib for crimes in Darfur during the early 2000s.
– Correct: True, based on recent events as of current knowledge.
– Importance: Unimportant.
– Relevance: False.
8. **Both SAF and RSF accused of fresh war crimes in the current conflict.**
– Correct: Plausible given the context, cannot confirm specific 2025 details.
– Importance: Lesser.
– Relevance: True.
9. **Calls for Comprehensive Peace Solutions**: Egyptian Foreign Minister stressed need for Sudanese-led peace process.
– Correct: Plausible but unverified specific to 2025.
– Importance: Unimportant.
– Relevance: False.
10. **Human Rights Organizations’ Role**: Groups like Human Rights Watch document war crimes and advocate for ICC expansion.
– Correct: Consistent with ongoing efforts, specifics for post-2023 unconfirmed.
– Importance: Lesser.
– Relevance: True.
Overall, the key points around mediation, regional dynamics, humanitarian impact, and justice are relevant, but few address the specific outcome of state-based conflict deaths reported by ACLED in Sudan in 2025.

Fact-checked summary:
The conflict in Sudan has led to significant humanitarian concerns, with millions displaced and severe impacts on infrastructure, services, and the civilian population. Reports have emerged of atrocities, including alleged chemical weapons use by the Sudanese Armed Forces (SAF). Both the SAF and Rapid Support Forces (RSF) have faced accusations of committing fresh war crimes within the ongoing conflict. These factors are expected to indirectly affect the death toll, although specifics for 2025 remain unconfirmed. The broader conflict reflects regional rivalries, with Egypt reportedly supporting the SAF and the UAE backing the RSF, which complicates mediation efforts. Human rights organizations continue to document these war crimes and advocate for broader accountability through bodies like the International Criminal Court.

OpenAI gives a base rate of number of deaths within defined categories (Carolyn‘s note: OpenAI failed to return a value.)
The question difficulty is rated 8 (0 to 10)
Historical weighted factors include:
0.30.20.20.10.2
A Bayesian calculation could be performed as follows:
The base rate of 0.4 was calculated using historical factors weighted by their relevance and likely impact. We then considered recent news: the atrocities and war crimes, regional support for factions, and humanitarian failures. For each factor, we estimated the likelihood of increased casualties, slightly increasing the base rate. P_new = (P_prior * Evidence) / (P_prior * Evidence + P_nonprior)
Bayesian base rate: 0.5 (Carolyn‘s note: In cases where the Multi-AI Oracle is only forecasting a single percent probability, this Bayesian rate is easy to understand, an adjustment to a probability. But in this case, with five probability buckets, I don’t understand what this means.)
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: 70
The following were considered in order to produce this base rate:
The base rate considers historical conflicts in Sudan, with the ongoing conflict severity compared to past situations. Given increased warfare intensity, documented war crimes, and regional involvements, the likelihood of death numbers falling into higher categories is significant.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional data on on-the-ground conditions, accurate death toll statistics, and real-time updates from humanitarian organizations would help refine the forecast. Insight into the effectiveness of ongoing diplomatic negotiations would also offer clarity.

Some potential divergent considerations that might affect the base rate:
The base rate may differ if an effective peace agreement is reached, or there is successful humanitarian intervention, which weren’t prominent factors in previous similar conflicts. Economic sanctions or a shift in regional alliances might also rapidly change outcomes.

The following chain of events are necessary for the question to resolve positively:
– Increase in conflict intensity (likely)
– Continuation or escalation of atrocities (likely)
– Failure of peace talks or mediation efforts (likely)
– Humanitarian aid failures leading to higher mortality (possible)

Querying Claude (AI predicts: [“Less than 1000”: 0.02, “Between 1000 and 3000”: 0.08, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.2] – 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”: 0.35, “More than 12000”: 0.15] – 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”: 0.14, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.5] – confidence: 6)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.082222222222222, Max: 0.23333333333333
# LLM responses: 3
Explanations of the above statistical measures here —>

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 predictions regarding the conflict in Sudan are based on the ongoing high-intensity clashes between the Sudanese Armed Forces (SAF) and the Rapid Support Forces (RSF), which have resulted in severe humanitarian crises, documented war crimes, and regional involvement by countries such as Egypt and UAE. Historical data and patterns suggest high casualty rates similar to previous Sudanese conflicts, further exacerbated by the failure of mediation efforts and ineffective humanitarian aid. However, these projections could be adjusted if significant changes occur, such as successful peace agreements, effective humanitarian interventions, shifts in regional alliances, or major international action that could mitigate the violence. Additionally, the accuracy of casualty estimates could be influenced by reporting discrepancies or changes in the conflict’s nature.

Runtime: 236 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.