Where do these coding results come from?

Both coding agents worked the same 24 merged changes from the private Stet-AI/stet repository, each in the real repo as it was before the change. The repo’s tests and judges graded every patch against the merged change; no public benchmark scores are used.

Are reasoning settings combined into one model score?

No. Each effort pairing keeps its own recorded quality call, head-to-head record, cost and agent time. Incompatible scores are never averaged.

Haiku 5.5 vs Muse Spark 1.3

Muse Spark 1.3 leads on quality in 1 of 2 pairings; the rest show no clear difference. 2 pairings; 24 merged changes in Stet-AI/stet. Compare the individual calls below to choose which setup to investigate.

What this comparison is

1 real repositoryStet-AI/stet, private; not public benchmark scores
24 merged changeseach run end to end by the coding agent from the repo as it was before the change
Graded against the merged changeby the repo’s own tests and by judges comparing each patch with it
Quality, cost and timea smaller sample than public benchmarks, but real agent work on a real codebase

Compare coding models Low vs high vs xhigh/max reasoning for coding agents

Recorded setup pairings

Each row is a separate recorded comparison. Scores are not pooled or averaged across effort settings. W/D/L means wins, draws and losses; undecided judgments remain undecided.

Stet score: A setup’s average chance of beating another setup on a task, from 0 to 100; 50 is even with the field.

Setup pairing	Recorded quality call and record	Quality evidence	Cost per task	Agent time per task
Haiku 5.5 max vs Muse Spark 1.3 highHaiku 5.5 max · max reasoningMuse Spark 1.3 high · high reasoning21/24 tasks observed by both setups.	No clear quality difference: Muse Spark 1.3 high won 4, Haiku 5.5 max won 3, 13 tied, 4 undecided; Muse Spark 1.3 high leads on cost and agent time: 7.8× cheaper and 4.4× faster.Head to head, Muse Spark 1.3 high won 4, tied 13 and lost 3 against Haiku 5.5 max, with 4 undecided.	No clear difference 3–4 head to head, 13 tiedHaiku 5.5 max: 48.2 (95% range 38.8–58.1)Muse Spark 1.3 high: 51.9 (95% range 47.9–56.0)	Haiku 5.5 max: $0.78 Muse Spark 1.3 high: $0.10	Haiku 5.5 max: 58.4 min Muse Spark 1.3 high: 13.2 min
Haiku 5.5 low vs Muse Spark 1.3 highHaiku 5.5 low · low reasoningMuse Spark 1.3 high · high reasoning22/24 tasks observed by both setups.	Muse Spark 1.3 high leads on quality: won 4, tied 17, lost 0, 3 undecided head to head; Haiku 5.5 low leads on cost and agent time: 1.6× cheaper and 1.3× faster.Head to head, Muse Spark 1.3 high won 4, tied 17 and lost 0 against Haiku 5.5 low, with 3 undecided.Not yet conclusive across all 136 comparisons on the board.	Clear lead 4–0 head to head, 17 tiedHaiku 5.5 low: 44.7 (95% range 39.5–49.1)Muse Spark 1.3 high: 51.9 (95% range 47.9–56.0)	Haiku 5.5 low: $0.06 Muse Spark 1.3 high: $0.10	Haiku 5.5 low: 9.9 min Muse Spark 1.3 high: 13.2 min

Setup pairing

Recorded quality call and record

Quality evidence

Cost per task

Agent time per task

Haiku 5.5 max vs Muse Spark 1.3 highHaiku 5.5 max · max reasoningMuse Spark 1.3 high · high reasoning21/24 tasks observed by both setups.

No clear quality difference: Muse Spark 1.3 high won 4, Haiku 5.5 max won 3, 13 tied, 4 undecided; Muse Spark 1.3 high leads on cost and agent time: 7.8× cheaper and 4.4× faster.Head to head, Muse Spark 1.3 high won 4, tied 13 and lost 3 against Haiku 5.5 max, with 4 undecided.

No clear difference
3–4 head to head, 13 tiedHaiku 5.5 max: 48.2 (95% range 38.8–58.1)Muse Spark 1.3 high: 51.9 (95% range 47.9–56.0)

Haiku 5.5 max: $0.78

Muse Spark 1.3 high: $0.10

Haiku 5.5 max: 58.4 min

Muse Spark 1.3 high: 13.2 min

Haiku 5.5 low vs Muse Spark 1.3 highHaiku 5.5 low · low reasoningMuse Spark 1.3 high · high reasoning22/24 tasks observed by both setups.

Muse Spark 1.3 high leads on quality: won 4, tied 17, lost 0, 3 undecided head to head; Haiku 5.5 low leads on cost and agent time: 1.6× cheaper and 1.3× faster.Head to head, Muse Spark 1.3 high won 4, tied 17 and lost 0 against Haiku 5.5 low, with 3 undecided.Not yet conclusive across all 136 comparisons on the board.

Clear lead
4–0 head to head, 17 tiedHaiku 5.5 low: 44.7 (95% range 39.5–49.1)Muse Spark 1.3 high: 51.9 (95% range 47.9–56.0)

Haiku 5.5 low: $0.06

Muse Spark 1.3 high: $0.10

Haiku 5.5 low: 9.9 min

Muse Spark 1.3 high: 13.2 min

Questions about these results

Which is better for coding, Haiku 5.5 or Muse Spark 1.3?: Muse Spark 1.3 leads on quality in 1 of 2 pairings; the rest show no clear difference. 2 pairings; 24 merged changes in Stet-AI/stet. Compare the individual calls below to choose which setup to investigate.
Where do these coding results come from?: Both coding agents worked the same 24 merged changes from the private Stet-AI/stet repository, each in the real repo as it was before the change. The repo’s tests and judges graded every patch against the merged change; no public benchmark scores are used.
Are reasoning settings combined into one model score?: No. Each effort pairing keeps its own recorded quality call, head-to-head record, cost and agent time. Incompatible scores are never averaged.