// head_to_head

Claude Opus 4.7 vs Kimi K3

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.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

Kimi K3 wins outright — it scores higher and costs less.

Kimi K3 leads by 2.7 points overall while listing 1.7× cheaper per blended million tokens. There is no trade-off to reason about here; the only reason to pick the other is a constraint this table does not show, like an existing contract, a region, or a provider you are already on. Kimi K3 also leads on measured cost per point of capability, at $0.1909 per point.

anthropic

Claude Opus 4.7

Blended / 1M
$10.00
Context
1M
Released
Apr 16, 2026
Overall score
76.5
reasoningtool callingimage inputfile inputprompt caching

moonshotai

Kimi K3

Blended / 1M
$6.00
Context
1.0M
Released
Jul 16, 2026
Overall score
79.2
reasoningtool callingimage inputvideo inputprompt caching

Specs and pricing

MetricClaude Opus 4.7Kimi K3
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

76.579.2win
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.2846$0.1909win
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$10.00$6.00win
Input price / 1M$5.00$3.00win
Output price / 1M$25.00$15.00win
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.500$0.300win
Context window1M1.0M
Max output tokens128K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Claude Opus 4.7 on top, Kimi K3 below, both out of 100.

Agentic coding
50.7
62.2
Codingtoo close to call
82.1
81.4
Reasoning
87.2
90.7
Mathematics
92.9
84.4
Data analysistoo close to call
78.3
78.7
Language
77.9
85.5
Instruction following
66.7
71.4

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.

WorkloadClaude Opus 4.7Kimi K3
Support chatbot

1.2K in / 400 out × 200K requests

$2876.00/mo$1725.60/mo
RAG assistant

8K in / 600 out × 100K requests

$3700.00/mo$2220.00/mo
Coding agent

40K in / 4K out × 20K requests

$3480.00/mo$2088.00/mo
Document extraction

20K in / 1.5K out × 50K requests

$6650.00/mo$3990.00/mo
Bulk classification

500 in / 20 out × 5M requests

$12,750/mo$7650.00/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

Kimi K3

Lowest measured cost per point of capability at $0.1909 per point — the gap compounds with every request.

Quality matters more than the bill

Kimi K3

Highest overall LiveBench score of the two at 79.2.

The workload is coding or agentic work

Kimi K3

Leads on agentic coding — 62.2 against 50.7.

Claude Opus 4.7 vs Kimi K3 FAQ

Which is better, Claude Opus 4.7 or Kimi K3?

Kimi K3 wins outright — it scores higher and costs less. Kimi K3 leads by 2.7 points overall while listing 1.7× cheaper per blended million tokens. There is no trade-off to reason about here; the only reason to pick the other is a constraint this table does not show, like an existing contract, a region, or a provider you are already on. Kimi K3 also leads on measured cost per point of capability, at $0.1909 per point.

Is Claude Opus 4.7 cheaper than Kimi K3?

Kimi K3 is cheaper. On a 3:1 input:output blend, Claude Opus 4.7 lists at $10.00 per million tokens and Kimi K3 at $6.00 — Kimi K3 is 1.7× cheaper. Input and output are priced separately — Claude Opus 4.7 charges $5.00 in and $25.00 out, Kimi K3 charges $3.00 and $15.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.

Claude Opus 4.7 vs Kimi K3: which scores higher on benchmarks?

Claude Opus 4.7 scores 76.5 and Kimi K3 scores 79.2 overall on LiveBench, the mean of its seven categories. That is a 2.7-point lead for Kimi K3. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.

Which gives better value for money, Claude Opus 4.7 or Kimi K3?

Kimi K3. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. Claude Opus 4.7 works out at $0.2846 per point and Kimi K3 at $0.1909.

Does Claude Opus 4.7 or Kimi K3 have a bigger context window?

They are effectively the same — 1M for Claude Opus 4.7 and 1.0M for Kimi K3.

Do Claude Opus 4.7 and Kimi K3 support prompt caching?

Both publish a cached-input rate: $0.500 per million for Claude Opus 4.7 and $0.300 for Kimi K3, against full input rates of $5.00 and $3.00. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.

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.
  • ScoresLiveBench 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.