// head_to_head
Kimi K2.7 Code vs Hermes 4 405B
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Kimi K2.7 Code is the cheaper of the two; neither can be ranked on quality here.
Hermes 4 405B does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
moonshotai
Kimi K2.7 Code
- Blended / 1M
- $1.35
- Context
- 262K
- Released
- Jun 12, 2026
- Overall score
- 68.4
nousresearch
Hermes 4 405B
- Blended / 1M
- $1.50
- Context
- 131K
- Released
- Aug 26, 2025
- Overall score
- Not evaluated
Specs and pricing
| Metric | Kimi K2.7 Code | Hermes 4 405B |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 68.4 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0545 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.35win | $1.50 |
| Input price / 1M | $0.706win | $1.00 |
| Output price / 1M | $3.30 | $3.00win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.180 | — |
| Context window | 262Kwin | 131K |
| Max output tokens | 236Kwin | 118K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Kimi K2.7 Code on top, Hermes 4 405B below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Kimi K2.7 Code | Hermes 4 405B |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $395.60/mo | $480.00/mo |
| RAG assistant 8K in / 600 out × 100K requests | $552.48/mo | $980.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $534.29/mo | $1,040/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $927.39/mo | $1,225/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,832/mo | $2,800/mo |
Which should you pick?
You need to fit large documents in one call
Kimi K2.7 Code
Wider context window — 262K against 131K.
Kimi K2.7 Code vs Hermes 4 405B FAQ
Which is better, Kimi K2.7 Code or Hermes 4 405B?
Kimi K2.7 Code is the cheaper of the two; neither can be ranked on quality here. Hermes 4 405B does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Kimi K2.7 Code cheaper than Hermes 4 405B?
Kimi K2.7 Code is cheaper. On a 3:1 input:output blend, Kimi K2.7 Code lists at $1.35 per million tokens and Hermes 4 405B at $1.50 — Kimi K2.7 Code is 11% cheaper. Input and output are priced separately — Kimi K2.7 Code charges $0.706 in and $3.30 out, Hermes 4 405B charges $1.00 and $3.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Kimi K2.7 Code or Hermes 4 405B have a bigger context window?
Kimi K2.7 Code has the larger context window: 262K for Kimi K2.7 Code against 131K for Hermes 4 405B. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Kimi K2.7 Code and Hermes 4 405B support prompt caching?
Kimi K2.7 Code publishes a cached-input rate of $0.180 per million tokens against a full input rate of $0.706. The catalogue lists no separate cached rate for Hermes 4 405B, which means the provider does not price it separately here — not that caching is unavailable.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.