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.

GPT 6.1 Sol vs GPT 6 Luna

GPT 6 Luna cheaper in both pairings. GPT 6.1 Sol leads on quality in every pairing. 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
GPT 6.1 Sol medium vs GPT 6 Luna maxGPT 6.1 Sol medium · medium reasoningGPT 6 Luna max · max reasoning23/24 tasks observed by both setups.	GPT 6.1 Sol medium leads on quality and agent time: won 3, tied 19, lost 0, 2 undecided head to head and 5.1× faster; GPT 6 Luna max leads on cost: 3.0× cheaper.Head to head, GPT 6.1 Sol medium won 3, tied 19 and lost 0 against GPT 6 Luna max, with 2 undecided.Not yet conclusive across all 136 comparisons on the board.	Clear lead 3–0 head to head, 19 tiedGPT 6.1 Sol medium: 54.1 (95% range 47.7–61.5)GPT 6 Luna max: 46.0 (95% range 40.4–51.6)	GPT 6.1 Sol medium: $1.10 GPT 6 Luna max: $0.37	GPT 6.1 Sol medium: 11.8 min GPT 6 Luna max: 59.7 min
GPT 6.1 Sol medium vs GPT 6 Luna lowGPT 6.1 Sol medium · medium reasoningGPT 6 Luna low · low reasoning23/24 tasks observed by both setups.	GPT 6.1 Sol medium leads on quality: won 7, tied 14, lost 1, 2 undecided head to head; GPT 6 Luna low leads on cost and agent time: 20.6× cheaper and 1.7× faster.Head to head, GPT 6.1 Sol medium won 7, tied 14 and lost 1 against GPT 6 Luna low, with 2 undecided.Not yet conclusive across all 136 comparisons on the board.	Clear lead 7–1 head to head, 14 tiedGPT 6.1 Sol medium: 54.1 (95% range 47.7–61.5)GPT 6 Luna low: 37.8 (95% range 27.8–47.7)	GPT 6.1 Sol medium: $1.10 GPT 6 Luna low: $0.05	GPT 6.1 Sol medium: 11.8 min GPT 6 Luna low: 6.9 min

Setup pairing

Recorded quality call and record

Quality evidence

Cost per task

Agent time per task

GPT 6.1 Sol medium vs GPT 6 Luna maxGPT 6.1 Sol medium · medium reasoningGPT 6 Luna max · max reasoning23/24 tasks observed by both setups.

GPT 6.1 Sol medium leads on quality and agent time: won 3, tied 19, lost 0, 2 undecided head to head and 5.1× faster; GPT 6 Luna max leads on cost: 3.0× cheaper.Head to head, GPT 6.1 Sol medium won 3, tied 19 and lost 0 against GPT 6 Luna max, with 2 undecided.Not yet conclusive across all 136 comparisons on the board.

Clear lead
3–0 head to head, 19 tiedGPT 6.1 Sol medium: 54.1 (95% range 47.7–61.5)GPT 6 Luna max: 46.0 (95% range 40.4–51.6)

GPT 6.1 Sol medium: $1.10

GPT 6 Luna max: $0.37

GPT 6.1 Sol medium: 11.8 min

GPT 6 Luna max: 59.7 min

GPT 6.1 Sol medium vs GPT 6 Luna lowGPT 6.1 Sol medium · medium reasoningGPT 6 Luna low · low reasoning23/24 tasks observed by both setups.

GPT 6.1 Sol medium leads on quality: won 7, tied 14, lost 1, 2 undecided head to head; GPT 6 Luna low leads on cost and agent time: 20.6× cheaper and 1.7× faster.Head to head, GPT 6.1 Sol medium won 7, tied 14 and lost 1 against GPT 6 Luna low, with 2 undecided.Not yet conclusive across all 136 comparisons on the board.

Clear lead
7–1 head to head, 14 tiedGPT 6.1 Sol medium: 54.1 (95% range 47.7–61.5)GPT 6 Luna low: 37.8 (95% range 27.8–47.7)

GPT 6.1 Sol medium: $1.10

GPT 6 Luna low: $0.05

GPT 6.1 Sol medium: 11.8 min

GPT 6 Luna low: 6.9 min

Questions about these results

Which is better for coding, GPT 6.1 Sol or GPT 6 Luna?: GPT 6 Luna cheaper in both pairings. GPT 6.1 Sol leads on quality in every pairing. 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.