G
Gemini 4 Argon
First overall on GPQA at 96.4 with a 4% hallucination rate — the strongest Gemini you can actually use
Intelligence v5
50.4
Leaderboard rank
#7
Input / output
$2.00/$10.00
Blended 3:1
$4.00
Output speed
80 tok/s
Value
13 pts/$
Capability profile Normalised to the field maximum
Specifications
Vendor
Google
Released
2026-10-13
Weights
Closed, API only
Context
1,000,000 tokens
Max output
Undisclosed
Parameters
Undisclosed
Input price
$2.00 / 1M
Output price
$10.00 / 1M
Cache hit
n/a
Output speed
80 tok/s
Intelligence
50.4（v5）
Benchmark scores
How it is measured →Ranked 7 · bars are scaled to the field maximum for that benchmark.
| Benchmarks | Score | Vs. best in field | Gap |
|---|---|---|---|
| AA Intelligence Index v5 Intelligence index | 50.4 | 85% | −9.0 pts |
| AA Intelligence Index v4.3.2 | — | — | not indexed |
| GPQA Diamond Graduate-level science reasoning | 96.4 | 100% | |
| Terminal-Bench 4.0 | — | — | not indexed |
| LiveBench Design Document generation (DOCX/PPT/PDF) | 73.7 | 85% | −13.2 pts |
| Vals Index Vals composite index | 70.36 | 96% | −2.7 pts |
Assessment
Available to Google AI Pro and Ultra users since 13 October, and first on the Arena text board among publicly available models. Mind the pricing: $2/$10 is promotional and reverts to $4/$20 on 2026-12-01 — double. Output pricing includes thinking tokens.
At the same price
The four models closest on blended price, side by side.
| Model | v5 | Blended | tok/s | Score gap |
|---|---|---|---|---|
| Claude Sonnet 5.5Anthropic | 54.2 | $4.00 | 135 | +3.8 |
| GPT-6.1 SolOpenAI | 54.5 | $4.00 | 77 | +4.1 |
| Gemini 4 CarbonGoogle | 59.4 | $4.00 | 87 | +9.0 |
| Muse WonderMeta | 43.3 | $4.00 | 143 | -7.1 |
Compare side by side
Line it up against other models on price, speed and every benchmark.
The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.
Open the comparison tool → Back to leaderboard