Gemini 4 Argon

GoogleProprietaryReleased Sep 30, 2026

On the arena.ai Agents leaderboard, Gemini 4 Argon has a Net Improvement of 10.83% (High, rank #8, 95% interval 9.96%–11.70%). Gemini 4 Argon ranks #2 on the LMArena Text leaderboard (style control) with an Arena score of 1522.4 (±5.5, 19,787 votes). Artificial Analysis Intelligence Index: 50.4. API price: $4.00 input / $20.00 output per 1M tokens. Context: 1.05M. Nearest rivals: Gemini 4 Carbon (1526.0) above and Muse Wonder (1511.0) below.

Quick answer

Agents leaderboard
#8 of 37 · 10.83% success
Text (LMArena)
#2 · 1522.4
17NAS overall
#8 of 36
API price (in / out)
$4.00 / $20.00 per 1M tokens
Data updated
Nov 10, 2026 · synced daily

Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter

Key metrics

Agent Net Improvement10.83%High53,301 sessions · #8
Arena score1522.4±5.5LMArena #2 · 19,787 votes
Intelligence50.4Variant: high
Coding59.4Artificial Analysis
Writing (creative)1534.7±10.2LMArena creative writing #1 / 419
List price in / out$4.00 / $20.00USD per 1M tokens
Lowest route$2.00 / $10.00Cheapest OpenRouter route
Context1.05Mtokens
Output speed82tok/sAA measured median
TTFT / first answer36 / 36sReasoning model: includes thinking

Rank history

LMArena rank, last 26 days
#1#3#5Oct 16Nov 10

#1 on Oct 16, #2 now; best #1 in this period.

Models ranked nearby

Sorted by Arena score
#ModelArenaIntel.Output $tok/s
1Gemini 4 Carbon1526.060.0$20.0089
2Gemini 4 ArgonThis page1522.450.4$20.0082
3Muse Wonder1511.043.6$20.00123
4Claude Opus 5.51506.159.1$20.0096
5Claude Fable 51503.9–$50.00–

More from Google

#ModelArenaIntel.Output $tok/s
1Gemini 4 Carbon1526.060.0$20.0089
9Gemini 3.8 Flash1497.530.8$3.75123
14Gemini 3.7 Flash1489.4–$3.75–
18Gemini 3.1 Pro Preview1486.7–$12.00128
19Gemini 3 Pro1485.6–$12.00–
22Gemini 3.6 Flash1482.5–$3.75–

Pricing

  • Official API list price: $4.00 input and $20.00 output per 1M tokens (USD).
  • At a typical 3:1 input-to-output ratio, the blended cost is about $8.00 per 1M tokens.
  • Among 79 models with an output price, it is the #64 cheapest.
  • The cheapest OpenRouter route charges $2.00 input / $10.00 output.

Sources & methodology

On the arena.ai Agents leaderboard, Gemini 4 Argon has a Net Improvement of 10.83% (High, rank #8, 95% interval 9.96%–11.70%).

  • arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
  • LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
  • Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
  • OpenRouter — Route prices, context length and listing date.

Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).

Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.

FAQ

How does Gemini 4 Argon do on the Agents leaderboard?

On the arena.ai Agents leaderboard, Gemini 4 Argon has a Net Improvement of 10.83% (High, rank #8, 95% interval 9.96%–11.70%).

What rank is Gemini 4 Argon right now?

Gemini 4 Argon is #2 on our leaderboard of 70 scored models (Arena score 1522.4); its raw LMArena rank is #2.

What does Gemini 4 Argon cost via API?

Input $4.00 / output $20.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $8.00 per 1M tokens.

How fast is Gemini 4 Argon?

Artificial Analysis measures about 82 output tokens per second, 36 s to the first token and 36 s to the first answer token; it is a reasoning model, so latency includes thinking time.

How close is Gemini 4 Argon to the models ranked next to it?

It is 3.6 points behind Gemini 4 Carbon (1526.0) and 11.4 points ahead of Muse Wonder (1511.0); gaps smaller than the confidence interval (±5.5) are not significant.

Is Gemini 4 Argon open source? Can it be self-hosted?

Gemini 4 Argon is a closed model, available only via official APIs or hosted services.

What is the context length of Gemini 4 Argon?

1.05M (1,048,576 tokens, as listed on OpenRouter).

Gemini 4 Argon vs Gemini 4 Carbon: which is better?

On the LMArena Text leaderboard Gemini 4 Argon scores 1522.4 and Gemini 4 Carbon scores 1526.0 (a 3.6-point gap, within the confidence interval, so not significant). Agent task success: Gemini 4 Argon 10.83%, Gemini 4 Carbon 16.63%. On price, Gemini 4 Argon costs $20.00 and Gemini 4 Carbon $20.00 per 1M output tokens.

Is there a cheaper model close to Gemini 4 Argon?

Among models within 15 Text points, none is currently more than 30% cheaper than Gemini 4 Argon on output price.

Where does the Gemini 4 Argon data come from and how often is it updated?

Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 10, 2026.

Related leaderboards