Grok 4.3 vs Kimi K3.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | Grok 4.3 | Kimi K3 | Winner |
|---|---|---|---|
| League Score | 73.7 | 70.6 | Grok 4.3 |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | 90.1 | 93.5 | Kimi K3 |
| Context (tokens) | 1000000 | 1048576 | Kimi K3 |
| Speed (tok/s) | 151.8 | 44.8 | Grok 4.3 |
| Price (blended $/1M) | $1.56 | $6.00 | Grok 4.3 (cheaper) |
Tale of the tape
| Spec | Grok 4.3 | Kimi K3 |
|---|---|---|
| Maker | xAI (SpaceXAI) | Moonshot AI |
| Released | Apr 30, 2026 | Jul 16, 2026 |
| League Score | 74 | 71 |
| Context | 1,000,000 tokens | 1,048,576 tokens |
| Max output | — | 131,072 |
| $/1M input | $1.25 | $3.00 |
| $/1M output | $2.50 | $15.00 |
| Weights | Closed | Open |
| Speed | 151.8 t/s | 44.8 t/s |
Head-to-head benchmarks (shared only)
| Benchmark | Grok 4.3 | Kimi K3 |
|---|---|---|
| GPQA Diamond | 90.1 | 93.5 |
Cost at three workloads
| Workload | Grok 4.3 | Kimi K3 |
|---|---|---|
| Light — 1M in / 250K out | $1.88 | $6.75 |
| Standard — 10M in / 2.5M out | $18.75 | $67.50 |
| Long-context — 50M in / 5M out | $75.00 | $225.00 |
The pick
Pick Grok 4.3 if you want the higher overall League Score; you want the lower running cost.
Pick Kimi K3 if you need the bigger context window; you want downloadable weights / self-hosting.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, Grok 4.3 or Kimi K3?
Grok 4.3 leads on overall League Score, 74 to 71 — a gap of 3 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, Grok 4.3 or Kimi K3?
Grok 4.3 is cheaper: $1.56 vs $6.00 blended per 1M tokens (3:1 input/output mix) — about 3.8x less per token.
Which has the bigger context window, Grok 4.3 or Kimi K3?
Kimi K3, with 1M of context against 1M for Grok 4.3.
Which is better at reasoning, Grok 4.3 or Kimi K3?
Kimi K3 leads on GPQA Diamond, 93.5% vs 90.1% on graduate-level science questions.
Are Grok 4.3 and Kimi K3 open source?
Grok 4.3 is closed weights — API access only; Kimi K3 is open weights — it can be downloaded and self-hosted.