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:
Okay, let’s tackle this query about the Sudan conflict in 2025. The user wants a summary based on current web results, including news, Wikipedia, official sites, and prediction markets. They also want any relevant data tables and time series info.
First, I’ll go through the provided search results to find the most recent and relevant information. The search results include recent news from April 2025, so that’s a good start. Result [1] from CSIS mentions that the Sudanese army reclaimed the presidential palace in Khartoum, which is a significant development. It also talks about the humanitarian crisis with famine warnings.
Result [7] from UN Women emphasizes the role of women in peace efforts, which might be important for the summary. The Wikipedia entries [2], [5], and [8] give background on the conflict’s timeline, participants, and casualties. Result [4] from Africa Center discusses the genocide declaration by the U.S. against the RSF and their international support, which adds depth to the geopolitical aspects.
Now, checking for prediction markets or economic data. The user mentioned Kalshi, Metaculus, Polymarket. In the search results, [3] and [6] are about LLM benchmarks but mention prediction markets briefly. For example, [3] talks about forecasting BTC prices but doesn’t relate to Sudan. [9] is a podcast transcript mentioning Polymarket in a different context (U.S. elections), so no relevant Sudan predictions there. It seems there’s no direct data from prediction markets on the Sudan conflict in the provided results.
So, I’ll focus on the news and official reports. The key points are the army’s recent gains, humanitarian crisis, international involvement, and the genocide declaration. The tables from Wikipedia can be summarized to show military control and casualties. Since there’s no time series data provided, I can’t include that, but I’ll structure the military control and casualty data into tables as per the query’s request.
I need to ensure citations are correctly applied. Each significant statement should reference the relevant source number. For example, the army’s capture of the palace is from [1], the famine warnings from [1] and [4], and the genocide declaration details from [4].
Putting it all together: start with a summary of the current status, then delve into military developments, humanitarian issues, international dynamics, and the genocide declaration. Include tables for military control and casualties, citing the sources. Since there’s no prediction market data available in the sources, note that it’s not found. Make sure to follow the format rules with headers, lists, and citations properly placed.
The Sudan conflict in 2025 remains a catastrophic humanitarian and military crisis, marked by shifting territorial control, widespread displacement, and international geopolitical tensions. Below is a synthesis of key developments and data from available sources:
—
### **Current Military and Political Dynamics**
– **Sudanese Armed Forces (SAF)** regained control of the presidential palace in Khartoum in April 2025, a symbolic victory against the Rapid Support Forces (RSF) [1][8]. The RSF retains control of southern Khartoum and Darfur, while the SAF advances toward consolidating central and eastern regions [1][4].
– **Risk of bifurcation**: The RSF has declared a parallel government, raising fears of a Libya-like split, with Darfur under RSF control and central/eastern Sudan under the SAF [1][8].
– **External backers**: The SAF is supported by Egypt, Iran, Saudi Arabia, and Türkiye, while the RSF receives funding and arms from the UAE and Wagner Group [4][8].
### **Humanitarian Crisis**
– **Displacement**: Over 15 million displaced (8.8 million internally, 3.5 million refugees) [4][8].
– **Famine risk**: 5 states, including Khartoum, face famine warnings, with 638,000 at immediate risk [1][4]. Humanitarian appeals are underfunded ($6 billion needed in 2025) [1].
– **Atrocities**: The U.S. has accused the RSF of genocide in Darfur, citing systematic killings of the Masalit ethnic group and sexual violence [4]. SAF leader al-Burhan is sanctioned for targeting civilians and obstructing aid [4].
###
**International Response**
– **Genocide designation**: The U.S. State Department’s January 2025 declaration against the RSF aims to pressure regional sponsors like the UAE [4].
– **Peace efforts**: No credible negotiations exist, though the UN and African Union advocate for inclusion of women-led initiatives [7].
—
### **Prediction Market and Forecast Data**
No explicit prediction market data (e.g., Kalshi, Polymarket) was found in the provided sources. Current analysis relies on governmental and NGO reports.
—
### **Key Risks Moving Forward**
1. **El Fasher siege**: A potential RSF takeover of this Darfur city could displace 1 million+ civilians [1].
2. **Famine acceleration**: Aid shortages and SAF/RSF obstructionism may worsen starvation [1][4].
3. **Regional spillover**: Chad hosts 950,000 Darfur refugees, straining resources [4].
The conflict’s trajectory hinges on external actors curtailing support to warring factions and urgent humanitarian mobilization. Without intervention, Sudan risks fragmentation and a generational loss of life.
OpenAI gives a base rate of proportion (Carolyn’s note: Below the Multi-AI Oracle gives a vague base rate of “internal African conflicts with international implications tend to have protracted resolutions.)
The question difficulty is rated 8 (0 to 10)
Sufficient news to provide a good forecast? 0 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: reference_class
Expected time (days) until question close: 180
The following were considered in order to produce this base rate:
The base rate considers the historical frequency of successful military campaigns leading to territorial recapture, the ongoing humanitarian crisis, and the political environment that rejects negotiation efforts. Historically, internal African conflicts with international implications tend to have protracted resolutions.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Access to detailed intelligence on internal military movements, diplomatic cables regarding foreign interventions, and a clear timeline of expected aid deliveries would enhance the forecast quality.
Some potential divergent considerations that might affect the base rate:
This forecast could diverge based on new international diplomatic efforts, shifts in foreign allegiance (e.g., UAE or Egypt changing support), or unexpected ceasefire agreements brokered by the EU or AU.
The following chain of events are necessary for the question to resolve positively: (Carolyn’s note: The bot is interpreting “positively” as meaning minimizing conflict deaths.)
– The Sudanese Armed Forces regaining control of key territories Likely
– Continuation of international support for SAF Moderately likely
– Resolution of internal conflict through peace negotiations Unlikely
– Effective humanitarian aid reaching famine-affected areas Possible
Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.24] – confidence: 6)
Querying Mistral (AI predicts: [“Less than 1000”: 0.05, “Between 1000 and 3000”: 0.15, “Between 3000 and 5000”: 0.25, “Between 5000 and 8000”: 0.3, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.05] – confidence: 6)
Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.01, “Between 3000 and 5000”: 0.03, “Between 5000 and 8000”: 0.1, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.65] – confidence: 7)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
Model value:
* Less than 1000: 1% (Carolyn’s note: Although currently there are reports of over 1000 fatalities, sometimes these numbers are adjusted downward due to new information)
* Between 1000 and 3000: 5%
* Between 3000 and 5000: 17%
* Between 5000 and 8000: 28%
* Between 8000 and 12000: 22%
* More than 12000: 27%
The various AI predictions regarding the conflict in Sudan highlight a severe and ongoing situation characterized by significant violence, a crippling humanitarian crisis, and complex international involvement. Key factors include the high death toll of over 61,000 in Khartoum, displaced populations of over 15 million, and widespread famine conditions. Military struggles between the Sudanese Armed Forces (SAF) and Rapid Support Forces (RSF) continue with limited success in peace negotiations. The international community, including the declaration of genocide by the U.S. against the RSF, adds layers of complexity to the conflict. However, the prediction could be proven wrong if unexpected breakthroughs occur, such as successful peace negotiations or shifts in foreign support and humanitarian aid that lead to de-escalation and improved conditions
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.
