Evidaxis

SWE-bench

repo reference measurement
Coding Agents · n = 20 · SWE-bench/SWE-bench
2 of 3 axes measurable · conf medium
convergence gate
Convergence gate: Gate: not computable — reference measurement Development velocity: rising vote Citation momentum: not measurable ∅ Direct-dependents momentum (deps.dev): measured ×
gate
1 of 3 axes

Gate: not computable — reference measurement

Gate: not computable — reference measurement
position in cohort distribution one of 20 in cohort
percentile 74 within cohort p25 p50 p75 p0 p100
percentile
p74
momentum averages present-axis z-scores; two- and three-axis scores are not strictly comparable
velocity z
velocity z gaugevelocity z+1.19 within cohort, log-slope +0.034/wk.0+1.19
velocity z
+1.19 σ
slope
+0.034/wk
log-slope +0.034/wk
citation z Citation source: not measured.
direct-dependents z
direct-dependents z gaugedirect-dependents z+0.00 within cohort, log-slope +0.018/point.0+0.00
direct-dependents z
+0.00 σ
slope
+0.018/point
Direct-dependents axis: measured.
cohort
20
systems measured
weekly commits
8
Development velocity axis: measured.
total citations
n/a
Citation source: not measured.
momentum
57.4
percentile p74
commit heatmap, last 26 weeks8/wk
weekly commits, 26 weeks26 weeks of commits, peak 53 in a week, 8 active weeks, 99 total.week 1: 0 commitsweek 2: 0 commitsweek 3: 0 commitsweek 4: 0 commitsweek 5: 0 commitsweek 6: 0 commitsweek 7: 1 commitsweek 8: 0 commitsweek 9: 0 commitsweek 10: 0 commitsweek 11: 0 commitsweek 12: 1 commitsweek 13: 1 commitsweek 14: 0 commitsweek 15: 0 commitsweek 16: 10 commitsweek 17: 53 commitsweek 18: 16 commitsweek 19: 1 commitsweek 20: 16 commitsweek 21: 0 commitsweek 22: 0 commitsweek 23: 0 commitsweek 24: 0 commitsweek 25: 0 commitsweek 26: 0 commits
weeks
26
peak/wk
53
active
8
total
99
citations by yearCitation source: not measured.
Daily dependents count (unscored) 7 dependents 6 direct, 1 indirect · pypi/swebench · deps.dev · the scored m4 axis uses weekly partitions

SWE-bench holds an Evidaxis momentum score of 57.4 of 100 on methodology m4, snapshot 2026-10-10, measured within the Coding Agents cohort (n = 20). Axis coverage: 2 of 3 axes measurable. Gate: not computable — reference measurement

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +58.12, regime accelerating. prior slope -0.003, recent slope -0.153 per week. -0.003prior 39w-0.153recent 13w+58.12×
swing
+58.12×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m4
commit Sharpereserved: <26 non-zero commit weeks
commit changepoint52 weekly commit points. Changepoint at week 43 (2026-08-08), slope change -3.916 commits per week.2026-08-08
date
week
43 of 52
Δslope
-3.916/wk
snapshot 1 of 1 · · m4
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m4
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m4
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m4
methodology gate snapshot 1 of 1 · · m4
commit weeks
52
citation years
0
shipped
2
reserved
4

shipped

  • recency-swing
  • commit-changepoint

reserved

  • commit-sharpe
  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m4

Daily dependents count (unscored)

SWE-bench dependents over time15 points, range 6 to 7 dependents.
min
6 dependents
max
7 dependents
latest
7 dependents
points
15

Downstream packages depending on pypi/swebench (deps.dev), captured point-in-time each snapshot. This daily series is unscored. The scored axis in m4 uses weekly partitions.

Measurement states

SWE-bench is under weekly measurement. History: 15 weekly observations; minimum 4. Development velocity axis: measured. Citation source: not measured. Direct-dependents axis: measured. Gate: not computable — reference measurement

Sources

SWE-bench/SWE-bench development-velocity axis

Others in Coding Agents

Agentless Coding Agents
1 of 3 axes measurable
46
p26
vel -0.30 cit no axis deps no axis
axis dials
-0.30 n/a n/a
Aider Coding Agents
2 of 3 axes measurable
46
p21
vel -0.05 cit no axis deps -0.60
axis dials
-0.05 n/a -0.60
ChatDev Coding Agents
1 of 3 axes measurable
50
p42
vel -0.04 cit no axis deps no axis
axis dials
-0.04 n/a n/a
Cline Coding Agents
2 of 3 axes measurable
49
p32
vel +0.33 cit no axis deps -0.49
axis dials
+0.33 n/a -0.49
Codex CLI Coding Agents
1 of 3 axes measurable
67
p95
vel +1.38 cit no axis deps no axis
axis dials
+1.38 n/a n/a
Continue Coding Agents
2 of 3 axes measurable
49
p37
vel +0.34 cit no axis deps -0.50
axis dials
+0.34 n/a -0.50

Full Coding Agents cohort →

Direct-dependents momentum (deps.dev)

Direct-dependents axis: measured.

Coverage state
scored
Cohort z
+0.00
OLS slope
+0.018
Theil-Sen slope
+0.017
Latest direct dependents
6
Confirmed-clean points
26
Reconstructed history points
15
As-of partition
2026-09-28
Fragility veto
inactive
Rising vote
no

This axis measures the trajectory of a system's own packages: declared in its own tree, published under that name, and not attributed by deps.dev to another repository. A package with no repository link is unverified and stays. The self-name exclusion list is fixed at the v2h.1 panel. Systems with no admitted package are not measured on this axis. Points that cannot be derived exactly are withheld, and the series restarts after a withheld point.

The earliest weekly points of each series were read from deps.dev's BigQuery history on 2026-07-21; later points are weekly captures. m4 does not replay those partitions: each point is the stored system total, one package's unique_direct, or a complete sketch union, and a point that is not exact is withheld. Each record reports how many of its points are reconstructed history.

Source: deps.dev (Google), CC-BY 4.0. Modified: aggregated to system-level counts and momentum scores.

Axis definition · Snapshot axis correlations

entity_id e_EF7QKB37YJK methodology m4 snapshot ad5e404d4f82 period 2026-w41 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m4, never edited by hand. Cite as: “Evidaxis, SWE-bench, entity e_EF7QKB37YJK, snapshot 2026-w41.”

Durable reference (format-independent): urn:evidaxis:claim:e_EF7QKB37YJK:m4:2026-10-10