Grok 4.3
xAI · released Apr 30, 2026
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Specification
- Context window
- 1M
- Max output
- —
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
37.9
85th percentile
Coding
42.2
Coding Index
Agentic
24.2
Agentic Index
Output speed
93 t/s
Median across providers
Latency
605ms
Time to first token
Cost per task
$0.26
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)97.7%
- GPQA Diamond90.1%
- IFBench81.3%
- AA-LCR (long context)66.0%
- SciCode47.3%
- Terminal-Bench Hard37.9%
- Humanity's Last Exam37.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 97.7% |
| GPQA Diamond | 90.1% |
| IFBench | 81.3% |
| AA-LCR (long context) | 66.0% |
| SciCode | 47.3% |
| Terminal-Bench Hard | 37.9% |
| Humanity's Last Exam | 37.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Opus 4.6Anthropic38.8
- MiMo-V2.5Xiaomi38.0
- Grok 4.20xAI38.0
- Grok 4.3xAI37.9
- Ling-3.0-flashInclusionAI37.8
- Qwen3.6 27BQwen37.7
- GPT-5.1OpenAI37.5
- Gemini 3.5 Flash LiteGoogle37.4
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Claude Opus 4.6 | 38.8 |
| MiMo-V2.5 | 38.0 |
| Grok 4.20 | 38.0 |
| Grok 4.3 | 37.9 |
| Ling-3.0-flash | 37.8 |
| Qwen3.6 27B | 37.7 |
| GPT-5.1 | 37.5 |
| Gemini 3.5 Flash Lite | 37.4 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $1.25
- Output / 1M tokens
- $2.5
- Cached input / 1M
- $0.2
- Blended 3:1
- $1.56
One task, estimated
$0.26
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,227
- Win rate
- 47.3%
- Strongest at
- UI components
- Tournaments
- 2,782
Elo by category
Dot position on a 1,025–1,250 scale · Elo has no meaningful zero
- 1,227
- 1,218
- 1,214
- 1,211
- 1,179
- 1,129
- 1,115
- 1,046
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1227 | 47.3% |
| Game development | 1218 | 48.9% |
| Websites | 1214 | 46.7% |
| Data visualisation | 1211 | 46.8% |
| 3D scenes | 1179 | 43.4% |
| SVG | 1129 | 40.9% |
| Mobile apps | 1115 | 37.4% |
| Full-stack apps | 1046 | 30.2% |