Claude Haiku 4.5
VS
Kimi K2.7 Code
Claude Haiku 4.5 vs Kimi K2.7 Code: which wins at real work?
22 task areas · same graded test runs · rank comparison only, so 0–100 and Elo collections never mix raw scores.
Kimi K2.7 Code wins 18 of 22 task areas we tested; Claude Haiku 4.5 takes 4. Kimi K2.7 Code costs 1.4× less per token ($4.24 vs $6 per 1M).
Kimi K2.7 Code costs 1.4× less per token ($4.24 vs $6 per 1M).
Task by task
| Task area | Claude Haiku 4.5 | Kimi K2.7 Code | Winner |
|---|---|---|---|
| Customer Support |
#99
/ 113
Usable
|
#10
/ 113
Strong
|
Kimi K2.7 Code |
| Presentations & Decks |
#88
/ 110
Strong
|
#5
/ 110
Excellent
|
Kimi K2.7 Code |
| RAG, Safety & Grounding |
#97
/ 113
Strong
|
#21
/ 113
Excellent
|
Kimi K2.7 Code |
| Executive Assistant |
#73
/ 112
Strong
|
#6
/ 112
Strong
|
Kimi K2.7 Code |
| Structured Output |
#109
/ 113
Usable
|
#46
/ 113
Excellent
|
Kimi K2.7 Code |
| Chef / Home Cooking |
#113
/ 126
Needs editing
|
#58
/ 126
Usable
|
Kimi K2.7 Code |
| Knowledge & Docs |
#71
/ 110
Usable
|
#16
/ 110
Excellent
|
Kimi K2.7 Code |
| Coding |
#94
/ 115
Usable
|
#41
/ 115
Strong
|
Kimi K2.7 Code |
| Investor & Pitch |
#63
/ 66
Needs editing
|
#15
/ 66
Strong
|
Kimi K2.7 Code |
| AI Strategy |
#91
/ 126
Strong
|
#44
/ 126
Strong
|
Kimi K2.7 Code |
| Frontend & Landing Pages |
#7
/ 109
Usable
|
#54
/ 109
Needs editing
|
Claude Haiku 4.5 |
| Landing Pages |
#61
/ 72
Usable
|
#17
/ 72
Strong
|
Kimi K2.7 Code |
| Content & Brand |
#89
/ 124
Usable
|
#48
/ 124
Strong
|
Kimi K2.7 Code |
| Creative & Comedy | #84 / 110 | #44 / 110 | Kimi K2.7 Code |
| Research & Competitive Analysis |
#59
/ 110
Usable
|
#20
/ 110
Excellent
|
Kimi K2.7 Code |
| Legal & HR |
#48
/ 110
Excellent
|
#14
/ 110
Excellent
|
Kimi K2.7 Code |
| Sales |
#80
/ 110
Usable
|
#48
/ 110
Usable
|
Kimi K2.7 Code |
| Product & Project Management |
#38
/ 110
Strong
|
#10
/ 110
Excellent
|
Kimi K2.7 Code |
| Data & Analytics |
#53
/ 110
Excellent
|
#31
/ 110
Excellent
|
Kimi K2.7 Code |
| Translation & Localization |
#27
/ 110
Excellent
|
#48
/ 110
Excellent
|
Claude Haiku 4.5 |
| Summarization & Meeting Notes |
#27
/ 110
Excellent
|
#47
/ 110
Excellent
|
Claude Haiku 4.5 |
| Training & Education |
#36
/ 110
Excellent
|
#39
/ 110
Excellent
|
Claude Haiku 4.5 |
Rank = position among every model config we tested in that task area (lower is better). Sorted by biggest gap first.
Frequently asked
Is Claude Haiku 4.5 better than Kimi K2.7 Code?
Across 22 task areas we benchmarked, Kimi K2.7 Code ranks higher in 18 and Claude Haiku 4.5 in 4.
Which is cheaper, Claude Haiku 4.5 or Kimi K2.7 Code?
Kimi K2.7 Code costs 1.4× less per token ($4.24 vs $6 per 1M).
What is Claude Haiku 4.5 better at?
Claude Haiku 4.5 out-ranks Kimi K2.7 Code at Frontend & Landing Pages, Translation & Localization, Summarization & Meeting Notes.
What is Kimi K2.7 Code better at?
Kimi K2.7 Code out-ranks Claude Haiku 4.5 at Customer Support, Presentations & Decks, RAG, Safety & Grounding.
More comparisons
This page is Spring Prompt, running in public
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals