Grok 4.3 vs Kimi K2.6.
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 K2.6 | Winner |
|---|---|---|---|
| League Score | 73.7 | 69.7 | Grok 4.3 |
| Coding (SWE-bench %) | — | 80.2 | — |
| Reasoning (GPQA %) | 90.1 | 90.5 | Kimi K2.6 |
| Context (tokens) | 1000000 | 262144 | Grok 4.3 |
| Speed (tok/s) | 151.8 | — | — |
| Price (blended $/1M) | $1.56 | $1.71 | Grok 4.3 (cheaper) |
Tale of the tape
| Spec | Grok 4.3 | Kimi K2.6 |
|---|---|---|
| Maker | xAI (SpaceXAI) | Moonshot AI |
| Released | Apr 30, 2026 | Apr 20, 2026 |
| League Score | 74 | 70 |
| Context | 1,000,000 tokens | 262,144 tokens |
| Max output | — | — |
| $/1M input | $1.25 | $0.95 |
| $/1M output | $2.50 | $4.00 |
| Weights | Closed | Open |
| Speed | 151.8 t/s | — |
Head-to-head benchmarks (shared only)
| Benchmark | Grok 4.3 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 90.1 | 90.5 |
Cost at three workloads
| Workload | Grok 4.3 | Kimi K2.6 |
|---|---|---|
| Light — 1M in / 250K out | $1.88 | $1.95 |
| Standard — 10M in / 2.5M out | $18.75 | $19.50 |
| Long-context — 50M in / 5M out | $75.00 | $67.50 |
The pick
Pick Grok 4.3 if you want the higher overall League Score; you need the bigger context window; you want the lower running cost.
Pick Kimi K2.6 if you want downloadable weights / self-hosting; coding is the priority.
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 K2.6?
Grok 4.3 leads on overall League Score, 74 to 70 — a gap of 4 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 K2.6?
Grok 4.3 is cheaper: $1.56 vs $1.71 blended per 1M tokens (3:1 input/output mix) — about 1.1x less per token.
Which has the bigger context window, Grok 4.3 or Kimi K2.6?
Grok 4.3, with 1M of context against 262.1K for Kimi K2.6.
Which is better at reasoning, Grok 4.3 or Kimi K2.6?
Kimi K2.6 leads on GPQA Diamond, 90.5% vs 90.1% on graduate-level science questions.
Are Grok 4.3 and Kimi K2.6 open source?
Grok 4.3 is closed weights — API access only; Kimi K2.6 is open weights — it can be downloaded and self-hosted.