How many conflict deaths will there be in Sudan in 2025?
Jeremy’s most recent version of his Multi-AI Oracle is a side competitor with the machine forecasting bots of the VIEWS competition.
Obtaining outside data. Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web: {think}
Okay, let’s start by understanding the user’s request. They want current web results about the Sudan conflict in 2025, including summaries and relevant data tables. The search results provided span from March 2025 back to older sources. I need to focus on the most recent information first.
Looking at the search results, source [1] from March 30, 2025, discusses the escalation in Sudan’s civil war and mentions South Sudan’s potential renewed conflict. The UN official’s dire warning here is crucial. Source [4] (CSIS analysis) from an unspecified 2025 date details the SAF recapturing the presidential palace, suggesting a new phase in the conflict. Source [5] (Wikipedia) updated to March 30, 2025, provides casualty numbers and territorial control. Source [2] (Simple Wikipedia) also has a military situation map as of March 31, 2025.
I should structure the answer with sections on current status, military developments, humanitarian crisis, and political context. Including a table from sources [2] and [5] showing military control and casualties makes sense. However, the user mentioned market prediction sites like Kalshi or Polymarket, but the provided sources don’t include these. Since there’s no data from those sites, I’ll note their absence but include available statistics.
It’s important to highlight the recent SAF advances in Khartoum, the RSF’s parallel government declaration, and the risk of famine. The summary should integrate key figures from the sources, like displacement numbers and casualties. Ensuring each fact is cited properly with the relevant source numbers is necessary. Also, checking dates to prioritize the most recent info, like the March 2025 updates, while older context provides background. Finally, making sure the tables are clear and sourced correctly without including unsupported data.
{/think}
The Sudan conflict in 2025 remains one of the world’s most severe humanitarian and geopolitical crises, marked by escalating violence, mass displacement, and a looming famine. Below is a synthesis of key developments and data from current sources:
—
## **Current Military and Political Status**
– **Sudanese Armed Forces (SAF)** retook control of Khartoum’s presidential palace in March 2025, marking a strategic victory against the Rapid Support Forces (RSF) after months of urban warfare[1][4]. The SAF aims to reclaim the entire capital and push the RSF back to Darfur[4].
– **Rapid Support Forces (RSF)** declared a parallel government in Nairobi, Kenya, in February 2025, while maintaining control over parts of Darfur and southern Khartoum suburbs[5]. Their supply-line weaknesses have accelerated territorial losses[4].
– **Ethnic divisions** persist, with SAF increasingly relying on Islamist networks and civilian militias, while the RSF faces allegations of systematic atrocities[1][5].*
—
## **Humanitarian Crisis**
– **Famine risk**: Five of Sudan’s 18 states, including Khartoum, face famine warnings due to blocked aid and insufficient funding[4]. Grass consumption is reported among starving families[1].
– **Displacement**: Over 13 million require humanitarian aid, with 30 million in need[4]. Refugee outflows to Chad, Egypt, and South Sudan continue[9].
– **International response**: The UN’s $6 billion appeal for 2025 is underfunded, worsening the assistance gap[4].
—
## **Regional and Historical Context**
– **South Sudan’s instability**: Delayed elections and unresolved ethnic tensions (Dinka vs. Nuer) threaten renewed civil war, per UN warnings[1][9].
– **Historical parallels**: The current conflict echoes Sudan’s Second Civil War (1983–2005), which killed 2 million and led to South Sudan’s independence[7][9].
—
### **Key Conflict Metrics Over Time (2023–2025)**
*Sources: [1][2][4][5][9]*
—
## **Projected Outcomes**
– **Military stalemate likely**: SAF advances in urban centers counterbalanced by RSF resilience in Darfur[4][5].
– **Bifurcation risk**: A Libya-like split between SAF-controlled east and RSF-controlled west grows probable[4].
– **No peace talks**: Both factions reject negotiation, prioritizing total victory[5].
—
Market prediction platforms like **Polymarket** or **Kalshi** showed no direct coverage of Sudan’s conflict in the provided sources. However, UN assessments and regional analysts broadly characterize the situation as a “dire” worsening trajectory[1][4].
OpenAI gives a base rate of (Carolyn’s note the base rate is discussed below but no percentages given because of poor data.)
The question difficulty is rated 8 (0 to 10)
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
(Carolyn’s note: the bot is confused. There are only 272 days left.)
The following were considered in order to produce this base rate:
The base rate is informed by the ongoing nature of Sudan’s conflict, characterized by entrenched positions held by both SAF and RSF, ongoing large-scale humanitarian needs, and historical difficulty in resolving such conflicts peacefully. Similar conflicts often persist without immediate resolution.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Information on potential diplomatic engagements, covert alliances or agreements, and shifts in support from regional or global powers would enhance forecast accuracy. Additionally, insights into any economic sanctions or aid provisions could impact the conflict’s evolution.
Some potential divergent considerations that might effect the base rate:
International diplomatic efforts or shifts in regional support could alter the trajectory. Additionally, significant battlefield advances or territorial gains by either side might change dynamics. External economic pressures or sanctions might also play a role in shifting positions.
The following chain of events are necessary for the question to resolve positively:
Reaching a peaceful resolution in Sudan’s conflict Unlikely – International intervention or mediation Possible – Internal restructuring of government powers or alliances Possible – RSF or SAF achieving a decisive military victory Uncertain
Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.05, “Between 5000 and 8000”: 0.12, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.55] – confidence: 6)
Querying Mistral (Error: Mistral is not returning an array)
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”: 0.2, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.39] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 2
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 3%
* Between 3000 and 5000: 8%
* Between 5000 and 8000: 16%
* Between 8000 and 12000: 25%
* More than 12000: 47%
The reasoning across the various AI analyses highlights a pessimistic outlook for the conflict in Sudan, pointing to ongoing escalation and a severe humanitarian crisis. There is a consensus that both the Sudanese Armed Forces (SAF) and the Rapid Support Forces (RSF) are entrenched in a stalemate, with significant resistance from both sides to engage in meaningful peace talks. This continued conflict has already resulted in over 61,000 deaths, particularly concentrated in the Khartoum State, with no decisive military outcome anticipated soon. However, the reasoning also acknowledges potential conditions under which the situation might improve, such as international pressure leading to peace efforts, resource depletion causing a de-escalation, or effective diplomatic interventions. Despite these possibilities, without significant changes in the current dynamics, high casualty rates and continued suffering seem likely.
Past forecasts on Sudan’s conflict fatalities —>
Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
Median: We collect the output values from the LLMs in an array. We then take the median value. This is between 0 and 1 (i.e. 0.15 = 15%).
Base rate: Currently we take OpenAI’s value as the base rate. We are working on a better value using a different prompt that takes into account process. The base rate helps to determine if the median makes sense.
SD: The standard deviation between the median and the base rate.
Confidence: We query each of the LLMs on how confident they are of their predictions (between 0 and 10) and take a median. Because the LLMs tend to be overconfident, we take anything lower than 6 as being low confidence. This factors into the overall model.
Conf Mode: Based on the confidence value. >=9 is high confidence. Below 6 is low confidence (this is also triggered by an exceptionally high SD).
Mellers: This refers to Barbara Mellers, specifically a paper she wrote that includes a formula for moving values towards an extreme (i.e. 0 or 1).
Reverse Mellers: This uses the formula from above, but with a sub-1 coefficient to move the values closer to 50%.
Theory of Mind: We ask the LLMs what they think other LLMs would predict. We hope that this makes them consider the questions more deeply.
Beta Distribution: Currently unused, but possibly of interest. This is based on the median, the base rate and the SD.
Close Type: We noticed that the appropriate base case for some questions is closer to the extremes, while others are closer to 50%. When we have a low confidence value, this helps us to determine whether to extremize or de-extremize the value. ‘A’ implies closer to zero. ‘B’ implies closer to 50%. ‘C’ implies closer to 100%.
# LLM Responses: The count of LLMs that responded. We query 5 currently, but they have a relatively high API failure rate.
Model value: For normal confidence mode, this is the median. For high confidence, this is the Mellers value. For low confidence, this is either the Mellers or Revers
Background on VIEWS: Near the end of 2024, the latest forecasting competition of the Violence and Impacts Early-Warning System (VIEWS) was launched. On Dec. 4, 2024, during a telecon, a group of machine forecasting experts involved in VIEWS observed Jeremy’s demonstration of his Multi-AI Oracle. Although it was too late for Jeremy to sign up as a VIEWS competitor, they urged him to run a side competition for everyone’s benefit. Jeremy chose their Sudan conflict deaths question.
Background on the Sudan conflict, as evaluated by the team of Jeremy Lichtman and Carolyn Meinel:
(1) The importance of the Sahel, a region in Africa that includes Sudan:
Why the Sahel Actually Matters (Possibly To You, Too)
(2) April 29, 2024: Today, a Russian diplomat is negotiating gold mining with the Sudanese Minister of Minerals.
(3) June 3, 2024: Today the African Union Announced Plans to Mediate in Sudan’s Civil War
(4) Sept. 11, 2024 Over 100K starvation deaths 96% likely in Sudan by 1 Jan 2025
Carolyn has checked Sudan’s news sites below to ensure that they are still in operation. However, given the widespread violence in Sudan, any of these could go offline without warning.
https://www.alnilin.com/
https://www.alrakoba.net/
https://www.altaghyeer.info/ar/
https://www.altaghyeer.info/en/
https://www.alttahrer.com/
https://www.alzaeemsd.com/
https://www.assayha.net
https://www.cover-sd.com/
https://kushnews.net/
https://rakobanews.com
https://www.sudanakhbar.com/
https://sudanjem.com/
https://suna-sd.net/en
https://sudantimes.net/
https://www.sudantribune.net/
https://www.sudantribune.com/
https://sudaneseonline.com/
https://www.sudanile.com/
https://sudanow-magazine.net/
https://www.sudaress.com/
https://www.tagpress.net/
Below, a screenshot from VIEWS forecasting conflict fatalities in Sudan through January 2028. Below that, satellite images of the devastation in Sudan.
Below, before and after pictures of the devastation of the civil war in Sudan.
