DeepSeek V4.1 Flash vs Haiku 5.5
DeepSeek V4.1 Flash 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 modelsLow 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 |
|---|---|---|---|---|
| DeepSeek V4.1 Flash max vs Haiku 5.5 maxDeepSeek V4.1 Flash max · max reasoningHaiku 5.5 max · max reasoning23/24 tasks observed by both setups. | No clear quality difference: DeepSeek V4.1 Flash max won 4, Haiku 5.5 max won 3, 15 tied, 2 undecided; DeepSeek V4.1 Flash max leads on cost and agent time: 1.6× cheaper and 1.2× faster.Head to head, DeepSeek V4.1 Flash max won 4, tied 15 and lost 3 against Haiku 5.5 max, with 2 undecided. | No clear difference 4–3 head to head, 15 tiedDeepSeek V4.1 Flash max: 50.4 (95% range 46.7–54.8)Haiku 5.5 max: 48.2 (95% range 38.8–58.1) | DeepSeek V4.1 Flash max: $0.49 (from 23/24 tasks) Haiku 5.5 max: $0.78 | DeepSeek V4.1 Flash max: 49.3 min Haiku 5.5 max: 58.4 min |
| DeepSeek V4.1 Flash max vs Haiku 5.5 lowDeepSeek V4.1 Flash max · max reasoningHaiku 5.5 low · low reasoning24/24 tasks observed by both setups. | DeepSeek V4.1 Flash max leads on quality: won 3, tied 20, lost 0, 1 undecided head to head; Haiku 5.5 low leads on cost and agent time: 7.6× cheaper and 5.0× faster.Head to head, DeepSeek V4.1 Flash max won 3, tied 20 and lost 0 against Haiku 5.5 low, with 1 undecided.Not yet conclusive across all 136 comparisons on the board. | Clear lead 3–0 head to head, 20 tiedDeepSeek V4.1 Flash max: 50.4 (95% range 46.7–54.8)Haiku 5.5 low: 44.7 (95% range 39.5–49.1) | DeepSeek V4.1 Flash max: $0.49 (from 23/24 tasks) Haiku 5.5 low: $0.06 | DeepSeek V4.1 Flash max: 49.3 min Haiku 5.5 low: 9.9 min |
Questions about these results
- Which is better for coding, DeepSeek V4.1 Flash or Haiku 5.5?
- DeepSeek V4.1 Flash 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.