Haiku 5.5 vs Opus 5
Haiku 5.5 cheaper in both pairings. Opus 5 leads on quality in every pairing; directional at this sample size. 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 |
|---|---|---|---|---|
| Haiku 5.5 max vs Opus 5 mediumHaiku 5.5 max · max reasoningOpus 5 medium · medium reasoning23/24 tasks observed by both setups. | Opus 5 medium leads on quality, 6–3 head to head with 13 tied and 2 undecided (directional at this sample size); Haiku 5.5 max leads on cost: 7.9× cheaper; Opus 5 medium leads on agent time: 2.5× faster.Head to head, Opus 5 medium won 6, tied 13 and lost 3 against Haiku 5.5 max, with 2 undecided. | Directional lead at this sample size 6–3 head to head, 13 tiedHaiku 5.5 max: 48.2 (95% range 38.8–58.1)Opus 5 medium: 58.2 (95% range 50.1–66.5) | Haiku 5.5 max: $0.78 Opus 5 medium: $6.13 | Haiku 5.5 max: 58.4 min Opus 5 medium: 23.2 min |
| Haiku 5.5 low vs Opus 5 mediumHaiku 5.5 low · low reasoningOpus 5 medium · medium reasoning24/24 tasks observed by both setups. | Opus 5 medium leads on quality: won 6, tied 16, lost 1, 1 undecided head to head; Haiku 5.5 low leads on cost and agent time: 95.3× cheaper and 2.3× faster.Head to head, Opus 5 medium won 6, tied 16 and lost 1 against Haiku 5.5 low, with 1 undecided.Not yet conclusive across all 136 comparisons on the board. | Clear lead 6–1 head to head, 16 tiedHaiku 5.5 low: 44.7 (95% range 39.5–49.1)Opus 5 medium: 58.2 (95% range 50.1–66.5) | Haiku 5.5 low: $0.06 Opus 5 medium: $6.13 | Haiku 5.5 low: 9.9 min Opus 5 medium: 23.2 min |
Questions about these results
- Which is better for coding, Haiku 5.5 or Opus 5?
- Haiku 5.5 cheaper in both pairings. Opus 5 leads on quality in every pairing; directional at this sample size. 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.