#02Google· released 2026-10-13

Google: Gemini 4 Argon.

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...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$2.00
Output $/1M
$10.00
Modality
audio · file · image · text · video
Arena Elo
1638
LMArena — human blind votes
AA Index
71.0
Artificial Analysis composite
LiveBench
89.3
Contamination-resistant
GPQA
94.0%
Grad-level science reasoning
MMLU-Pro
92.1%
Broad knowledge
SWE-bench
80.4%
Real GitHub bugs (Verified)
Terminal-Bench
66.8%
Agentic shell tasks
ARC-AGI
49.5%
Abstract reasoning
Aider Polyglot
85.7%
Multi-language code editing
Speed
72 tok/s
Median output speed

Profile

Google: Gemini 4 Argon is Google's entry at position #2 on the current aggregated leaderboard. Its strongest signals are human preference voting, graduate-level science reasoning, real-world software engineering, and unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard