Gemini 4 Argon
Google · released Oct 13, 2026
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
Specification
- Context window
- 1.05M
- Max output
- 66K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 2
- Moderated
- No
- Uptime
- 100.0%
Intelligence
52.6
99th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
76 t/s
Median across providers
Latency
1.58s
Time to first token
Cost per task
$0.90
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
- AA-LCR (long context)79.7%
- SciCode61.8%
- Humanity's Last Exam57.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AA-LCR (long context) | 79.7% |
| SciCode | 61.8% |
| Humanity's Last Exam | 57.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Sonnet 5.5Anthropic56.0
- Claude Fable 5.1Anthropic53.4
- GPT-6 AstraOpenAI52.7
- Gemini 4 ArgonGoogle52.6
- Muse WonderMeta52.4
- GPT-6.1 SolOpenAI51.8
- Claude Opus 5Anthropic50.8
- Claude Fable 5Anthropic49.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Claude Sonnet 5.5 | 56.0 |
| Claude Fable 5.1 | 53.4 |
| GPT-6 Astra | 52.7 |
| Gemini 4 Argon | 52.6 |
| Muse Wonder | 52.4 |
| GPT-6.1 Sol | 51.8 |
| Claude Opus 5 | 50.8 |
| Claude Fable 5 | 49.6 |
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
- $2
- Output / 1M tokens
- $10
- Cached input / 1M
- $0.1
- Blended 3:1
- $4
One task, estimated
$0.90
- 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
- 1,387
- Win rate
- 64.0%
- Strongest at
- 3D scenes
- Tournaments
- 455
Elo by category
Dot position on a 1,300–1,400 scale · Elo has no meaningful zero
- 1,387
- 1,369
- 1,324
- 1,307
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1387 | 64.0% |
| Game development | 1369 | 62.0% |
| Websites | 1324 | 56.4% |
| UI components | 1307 | 51.4% |