GPQA DiamondVerified
88%
GPQA Diamond accuracy
Models / xAI
Grok 4.3
Grok · Released 2026-04-30
Not the smartest model on the board, but the only one with a 2M context and a live social graph.
Default model for real-time social signals, very long context (>1M), and freshness-sensitive research where minutes matter.
Composite61
Context2M
Input / 1M$5.0
Output / 1M$25
Knowledge cutoff2026-03-15
Output speed103 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
70/100 avg
- Reasoning
- 88
- Coding
- 48
- Long context
- 73
3 tested benchmark families
Editor's note
Grok 4.3 is the only model on the public market with a real >1M context. The 2M window is real — but in our long-document tests, citation fidelity past 1.5M tokens drops sharply. The X search integration is a genuine differentiator for breaking-news research.Benchmark placements
Per-benchmark positions
Where Grok 4.3 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| SciCode | Coding | #54/ 97 | 48 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #55/ 186 | 37 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #57/ 195 | Artificial Analysis | 2026-10-12 | |
| GPQA Diamond | Reasoning | #65/ 184 | 88 | GPQA Diamond paper leaderboard | 2026-05-15 |
| AA-LCR | Long context | #104/ 184 | 73 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Grok 4.3 shows up, it's highlighted.
ReasoningGrok 4.3 · 88
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingGrok 4.3 · 48
- 174
- 273
- 370
Long contextGrok 4.3 · 73
- 189
- 286
- 385
Newest receipts
4 recentLast 120 days
Benchmark rows added to the public ledger for Grok 4.3 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 103 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 73% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 37.2% | Artificial Analysis | 24 |
| SciCode | Coding | 48.3% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Grok 4.3 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Grok 4.3. Scores link to the original source; gaps mean no public row exists yet.
5 of 13 catalog benchmarks have a sourced row for Grok 4.3.
Reasoning
Humanity's Last ExamVerified
37.2%
HLE (AA run)
Coding
SciCodeVerified
48.3%
SciCode (AA run)
Long context
AA-LCRVerified
73%
AA-LCR (AA run)
Performance
AA output speedVerified
103 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Released Grok 4.3 with 2M context and real-time X search.
- Grok 4.20 retired from general availability.
Sources
Where the numbers come from
- xAI pricing· checked 2026-06-01
- Grok 4.3 release· checked 2026-06-01
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Grok 4.3?
Grok 4.3 is a xAI model: Not the smartest model on the board, but the only one with a 2M context and a live social graph.
What is Grok 4.3 for?
Default model for real-time social signals, very long context (>1M), and freshness-sensitive research where minutes matter.
What does Grok 4.3 cost?
Grok 4.3 lists $5.0 input and $25 output per 1M tokens. Pricing last checked 2026-06-01.
How large is the Grok 4.3 context window?
Grok 4.3 publishes a 2M token context window.
What is the VerdictPal status of Grok 4.3?
Grok 4.3 carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.