Botmaster Phil Godzin’s Sudan conflict deaths forecast, Sept. 19, 2025

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

Phillip Godzin’s pgodzinai predicts today:

Less than 1,000: 1%
Between 1,000 and 3,000: 2%
Between 3,000 and 5,000: 22%
Between 5,000 and 8,000: 45%
Between 8,000 and 12,000: 23%
More than 12,000: 7%

15–19 minutes read (This is a condensed version of pgodzinai’s results Full rationale here—>)

Perplexity response:

## Key Citations and Analysis
Current Military Developments (September 2025)**
*Source: Critical Threats, September 18, 2025*
Recent reporting indicates ongoing military operations with SAF gains in central Sudan and continued RSF activities. The analysis references armed conflict data showing sustained violence patterns, though specific 2025 Sudan casualty figures aren’t provided in the available excerpt.[2]

**Data Limitations:** The most recent specific ACLED death toll cited is from November 2024 (28,700 cumulative deaths). No 2025-specific annual death tolls were found in the search results, making precise forecasting challenging without access to real-time ACLED data.

Grok response:

1. **Title:** Africa Overview: September 2025 | ACLED
**Description:** ACLED’s monthly update on conflict trends across Africa, focusing on violence in regions like Sudan.
**Date of Publication:** September 5, 2025.
**3-Sentence Summary:** This report highlights a surge in targeted violence in Darfur, driving an increase in civilian deaths linked to state-based conflicts in August 2025, with preliminary figures suggesting over 1,000 deaths in that month alone. It provides year-to-date data for Sudan, estimating around 3,500 state-based conflict deaths by mid-September 2025, based on ongoing battles between the Sudanese Armed Forces and Rapid Support Forces. The overview notes historical volatility, with similar spikes in 2024 (e.g., 2,500 deaths in Q3 2024), emphasizing the need for continued monitoring as conflicts escalate.
2. **Title:** UN Report Details Worsening Crisis in Sudan
**Description:** A UN human rights office analysis of the humanitarian and conflict situation in Sudan, based on verified data.
**Date of Publication:** September 19, 2025 (published 3 hours ago, as per recent web access).
**3-Sentence Summary:** The report documents at least 3,384 civilian deaths from state-based conflicts in the first half of 2025, primarily in Darfur, attributing most to clashes between armed groups. It highlights a sharp escalation in violence since June 2025, with monthly deaths averaging over 500, potentially pushing year-to-date totals toward 5,000 or more. Expert opinions from UN officials warn of further increases without a ceasefire, drawing on 2024 data where similar conflicts resulted in 4,000 deaths.
3. **Title:** Sudanese Civil War (2023–Present) – Wikipedia
**Description:** An overview of the ongoing civil war in Sudan, including statistics on deaths and conflict dynamics.
**Date of Publication:** September 4, 2025.
**3-Sentence Summary:** The page updates with 2025 data, reporting approximately 150,000 total deaths since 2023, with state-based conflicts in 2025 alone exceeding 3,000 by August. It cites ACLED sources for a breakdown, noting a 20% increase in deaths from 2024’s Q2 (around 1,200 deaths) due to renewed fighting in Khartoum and Darfur. Experts referenced in the article, including UN analysts, describe the conflict as one of the deadliest in the Horn of Africa, with potential for further escalation based on historical patterns.
4. **Title:** Sudan Conflict Timeline
**Description:** A chronological summary of battles, ceasefires, and casualty figures in Sudan’s civil war from 2023 to 2025.
**Date of Publication:** September 18, 2025 (1 day ago).
**3-Sentence Summary:** This timeline details key events in 2025, including a major offensive in July that led to over 1,000 state-based conflict deaths, as per ACLED estimates. It compares this to 2024, where deaths fluctuated between 500 and 1,500 per quarter, showing seasonal spikes in Q3 due to dry season fighting. The analysis includes expert warnings from humanitarian organizations about the risk of exceeding 5,000 deaths by year-end if current trends continue.

Extracted resolution criteria links:
[‘https://acleddata.com/conflict-watchlist-2025/sudan/‘, ‘https://acleddata.com/africa/horn-of-africa/sudan/‘]

Claude Vision analysis response:
## Current Death Toll Data (as of September 14, 2024):
– **Total reported fatalities**: 24,850 since April 15, 2023
– This represents deaths over approximately 17 months of conflict

## Recent Trends and Patterns:
The page shows a bar chart of “Reported fatalities by week” which displays weekly death counts over time. While specific dates aren’t clearly labeled on the x-axis, the chart shows:
– Significant variability in weekly fatalities
– Several major spikes reaching approximately 600-800 deaths in peak weeks
– More typical weeks showing 100-400 deaths
– The most recent data points (toward the right of the chart) appear to show continued substantial fatality levels

Anthropic response:
**Current Status and Historical Context:**

The most authoritative data comes from ACLED’s own visualization showing 24,850 total fatalities from April 15, 2023 through September 14, 2024 – approximately 17 months of conflict. This yields an average monthly rate of about 1,460 deaths. Multiple sources, including the UN report and ACLED’s September 2025 overview, indicate approximately 3,500 state-based conflict deaths have occurred in Sudan from January through mid-September 2025. This suggests a current run rate of roughly 390-430 deaths per month in 2025, representing a significant decrease from the 2023-2024 average.

The conflict dynamics show clear patterns: seasonal variations with higher violence during dry seasons (Q3-Q4), geographic concentration in Darfur and Khartoum, and involvement of well-organized forces (SAF and RSF) that maintain sustained fighting capacity. The August 2025 surge that reportedly killed over 1,000 civilians in a single month demonstrates the conflict’s capacity for rapid escalation.

**Projecting Forward:** With 3.5 months remaining in 2025 (mid-September to December), the key question is whether the conflict will maintain its current intensity, escalate, or decelerate. Historical patterns from 2024 show Q4 typically sees increased fighting – the 2024 Q4 period reportedly saw around 2,000 deaths. The humanitarian crisis continues to worsen, with half of Sudan’s population facing famine and a severe cholera outbreak, conditions that often correlate with sustained or increased conflict intensity.

Starting from approximately 3,500 deaths by mid-September, different scenarios yield different year-end totals:
– Maintaining current pace (400 deaths/month): ~4,900 total
– Modest escalation matching 2024 Q4 patterns (600 deaths/month): ~5,600 total
– Significant escalation like August 2025 (1,000+ deaths/month): ~7,000+ total
– Deceleration due to exhaustion or intervention (200 deaths/month): ~4,200 total

**Statistical Analysis:**
The weekly fatality chart from ACLED shows high variance, with peaks reaching 600-800 deaths per week and valleys around 100-200. This volatility, combined with the seasonal patterns and recent escalation in August 2025, suggests the conflict retains significant escalatory potential. The standard deviation appears to be roughly 40-50% of the mean, indicating substantial unpredictability in short-term death tolls.

Less than 1,000: 1%
Between 1,000 and 3,000: 2%
Between 3,000 and 5,000: 22%
Between 5,000 and 8,000: 45%
Between 8,000 and 12,000: 23%
More than 12,000: 7%

GPT Multiple Choice JSON response:

Rationale and key inputs
– Core data point I use as the baseline: multiple recent sources (ACLED summaries cited by UN and news outlets) indicate roughly 3,300–3,600 ACLED-recorded state-based conflict deaths in Sudan through mid-September 2025. I treat ~3,500 YTD (through ~Sept 19) as the best current estimate, with some uncertainty ±200–400 due to reporting lag and reconciliation. This is already above the two lower bins (<1000 and 1000–3000), so those are essentially ruled out.
– Time remaining to change the 2025 calendar-year total: about 3.5 months (from Sept 19 to Dec 31). Historically in this conflict (2023–2025) monthly death counts have varied a lot, with multi-week spikes of several hundred deaths and quieter weeks with a few dozen. Relevant patterns: Q3 and Q4 tend to produce higher fatalities (dry-season mobility and offensives), while the rainy season temporarily reduces rates in some regions. Recent reporting (Aug–Sept 2025) documents renewed offensives in Darfur and Khartoum-area fighting, suggesting elevated rates in the short term.
– Simple scenario arithmetic (starting from ~3,500 by mid‑September):
– Low continuation (roughly 300–500 deaths/month Oct–Dec): +1,000–1,500 → year total ≈ 4,500–5,000 (falls near the 3,000–5,000 or lower 5,000–8,000 boundary).
– Moderate continuation (roughly 700–900 deaths/month): +2,400–3,200 → year total ≈ 5,900–6,700 (squarely in 5,000–8,000).
– High escalation (roughly 1,000–1,500 deaths/month or a few large mass-casualty episodes): +3,500–5,250 → year total ≈ 7,000–8,750 (could reach 8k+).
– Extreme surge (major new offensives or mass-casualty events lasting months): could push totals above 12,000 but that requires sustained, very high monthly death rates (2,000+/month) and/or catastrophic single events; I assess that as unlikely in the remaining months but not impossible.

Two key assumptions whose failure would change the forecast most
1) Assumption: The reported mid‑September ACLED YTD (~3,500) is close to correct (±~500). Probability this is wrong by enough to change bin: 10%. If this fails (actual YTD much higher), the forecast would shift toward higher bins; if actual YTD is much lower, it would shift lower (but lower is unlikely given multiple independent sources).
2) Assumption: Monthly death rates Oct–Dec 2025 will be in the 300–1,200 range (i.e., remain high but not explode to multiple thousands per month). Probability this assumption fails (either severe drop due to ceasefire or severe surge): 30%. If it fails toward a sharp drop, the 3,000–5,000 bin becomes more likely; if it fails toward surge, the 5,000–8,000 or 8,000–12,000 bins gain probability.

My judgment and probability distribution
Given the solid base of ~3.5k by mid‑September and the historical tendency for Q4 to be at least as lethal as Q3 in this conflict, the modal outcome is that 2025 ends in the 5,000–8,000 band. There is a reasonable chance (but smaller) that continued but not explosive violence keeps the final count in 3,000–5,000. There is a nontrivial tail risk of larger escalation pushing totals into 8k–12k; a >12k outcome in the remaining 3+ months is unlikely but not impossible (would require extraordinary sustained monthly fatality rates).

Final probabilities (sum = 100%)

Less than 1,000: 1%
Between 1,000 and 3,000: 1%
Between 3,000 and 5,000: 35%
Between 5,000 and 8,000: 45%
Between 8,000 and 12,000: 12%
More than 12,000: 6%

Model’s Answer:

**Current Status and Historical Context:**
The most authoritative data comes from ACLED’s own visualization showing 24,850 total fatalities from April 15, 2023 through September 14, 2024 – approximately 17 months of conflict. This yields an average monthly rate of about 1,460 deaths. Multiple sources, including the UN report and ACLED’s September 2025 overview, indicate approximately 3,500 state-based conflict deaths have occurred in Sudan from January through mid-September 2025. This suggests a current run rate of roughly 390-430 deaths per month in 2025, representing a significant decrease from the 2023-2024 average.

The conflict dynamics show clear patterns: seasonal variations with higher violence during dry seasons (Q3-Q4), geographic concentration in Darfur and Khartoum, and involvement of well-organized forces (SAF and RSF) that maintain sustained fighting capacity. The August 2025 surge that reportedly killed over 1,000 civilians in a single month demonstrates the conflict’s capacity for rapid escalation.

**Projecting Forward:**
With 3.5 months remaining in 2025 (mid-September to December), the key question is whether the conflict will maintain its current intensity, escalate, or decelerate. Historical patterns from 2024 show Q4 typically sees increased fighting – the 2024 Q4 period reportedly saw around 2,000 deaths. The humanitarian crisis continues to worsen, with half of Sudan’s population facing famine and a severe cholera outbreak, conditions that often correlate with sustained or increased conflict intensity.

Starting from approximately 3,500 deaths by mid-September, different scenarios yield different year-end totals:
– Maintaining current pace (400 deaths/month): ~4,900 total
– Modest escalation matching 2024 Q4 patterns (600 deaths/month): ~5,600 total
– Significant escalation like August 2025 (1,000+ deaths/month): ~7,000+ total
– Deceleration due to exhaustion or intervention (200 deaths/month): ~4,200 total

**Key Uncertainties and Assumptions:**
The first critical assumption is that the ~3,500 death figure for 2025 through mid-September is accurate. This comes from multiple sources but shows some variation – the UN cites 3,384 for the first half of 2025 alone, while ACLED’s September overview suggests 3,500 year-to-date. If the actual figure is significantly higher (say 4,500-5,000), this would push all projections upward. I assess a 25% probability that current deaths are underreported by 30% or more.

The second assumption is that no major military breakthrough or international intervention occurs. The conflict has shown remarkable persistence despite various ceasefire attempts. However, if either SAF or RSF achieved a decisive victory, or if effective international peacekeeping forces deployed, death rates could drop dramatically. Conversely, a major offensive by either side could cause deaths to spike. I estimate a 20% probability of a game-changing event (either escalatory or de-escalatory) in the remaining months.

The third assumption is that ACLED’s reporting methodology and coverage remains consistent. In active conflict zones, data collection can be disrupted, and retrospective adjustments are common. ACLED might revise 2025 figures upward when they conduct their year-end review. I assess a 15% probability that methodological factors could cause the final reported number to differ substantially from real-time estimates.

**Statistical Analysis:** The weekly fatality chart from ACLED shows high variance, with peaks reaching 600-800 deaths per week and valleys around 100-200. This volatility, combined with the seasonal patterns and recent escalation in August 2025, suggests the conflict retains significant escalatory potential. The standard deviation appears to be roughly 40-50% of the mean, indicating substantial unpredictability in short-term death tolls.

Given the current baseline of ~3,500 deaths, the historical patterns, the ongoing humanitarian crisis, and typical Q4 escalation patterns, the most likely outcome appears to be in the 5,000-8,000 range, with meaningful probability mass in adjacent categories. The “Less than 1000” option is essentially impossible given we’re already at 3,500. The “Between 1000 and 3000” option would require significant data revision downward, which is highly unlikely. The extreme high end (“More than 12000”) would require unprecedented escalation – reaching 12,000 would need over 2,400 deaths per month for the remainder of 2025, far exceeding recent patterns.

Less than 1,000: 1%
Between 1,000 and 3,000: 2%
Between 3,000 and 5,000: 22%
Between 5,000 and 8,000: 45%
Between 8,000 and 12,000: 23%
More than 12,000: 7%

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 competitors. Our botmasters, Phil Godzin and Jeremy Lichtman, are conducting a side experiment with VIEWS.