DeepSeek V4.1 Flash (10/17) vs Haiku 5.5
DeepSeek V4.1 Flash (10/17) has a slight quality edge in 1 of 2 pairings; none is a clear lead. 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 (10/17) max vs Haiku 5.5 maxDeepSeek V4.1 Flash (10/17) max · codex · max reasoningHaiku 5.5 max · max reasoning21/24 tasks observed by both setups. | No clear quality difference: Haiku 5.5 max won 4, DeepSeek V4.1 Flash (10/17) max won 3, 16 tied, 1 undecided; DeepSeek V4.1 Flash (10/17) max leads on cost and agent time: 2.8× cheaper and 1.6× faster.Head to head, Haiku 5.5 max won 4, tied 16 and lost 3 against DeepSeek V4.1 Flash (10/17) max, with 1 undecided. | No clear difference 3–4 head to head, 16 tiedDeepSeek V4.1 Flash (10/17) max: 48.3 (95% range 42.9–53.4)Haiku 5.5 max: 48.8 (95% range 38.6–58.7) | DeepSeek V4.1 Flash (10/17) max: $0.28 Haiku 5.5 max: $0.78 | DeepSeek V4.1 Flash (10/17) max: 37.2 min Haiku 5.5 max: 58.4 min |
| DeepSeek V4.1 Flash (10/17) max vs Haiku 5.5 lowDeepSeek V4.1 Flash (10/17) max · codex · max reasoningHaiku 5.5 low · low reasoning22/24 tasks observed by both setups. | DeepSeek V4.1 Flash (10/17) max has a slight quality edge, 3–0 head to head with 21 tied; Haiku 5.5 low leads on cost and agent time: 4.4× cheaper and 3.8× faster.Head to head, DeepSeek V4.1 Flash (10/17) max won 3, tied 21 and lost 0 against Haiku 5.5 low. | Slight edge 3–0 head to head, 21 tiedDeepSeek V4.1 Flash (10/17) max: 48.3 (95% range 42.9–53.4)Haiku 5.5 low: 44.8 (95% range 39.0–50.1) | DeepSeek V4.1 Flash (10/17) max: $0.28 Haiku 5.5 low: $0.06 | DeepSeek V4.1 Flash (10/17) max: 37.2 min Haiku 5.5 low: 9.9 min |
Questions about these results
- Which is better for coding, DeepSeek V4.1 Flash (10/17) or Haiku 5.5?
- DeepSeek V4.1 Flash (10/17) has a slight quality edge in 1 of 2 pairings; none is a clear lead. 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.