Gemini 4 Argon

ARC Prize Verified
Google·Oct 13, 2026·6 harness configurations·$2 input / $10 output per 1M tokens

Gemini 4 Argon's best semi-private scores are 98.5% on v1 and 91.2% on v2, both at high reasoning. On v3, it reaches 49.8% with the Standard harness at low reasoning and 97.5% with the Provider Adapter harness at low reasoning. API issues prevented complete v3 evaluation with the standard harness. Runs completed on 42 of 55 tasks at low reasoning, 46 of 55 at medium reasoning, and 19 of 55 at high reasoning. Reported scores include all 55 tasks, retaining partial credit earned on incomplete runs. We excluded the high-reasoning standard-harness point from the chart because of this incomplete coverage. Reported costs use Google's introductory pricing of $2 per million input tokens and $10 per million output tokens.

Related models: Gemini 3.8 Flash, Gemini 3.7 Flash

ARC-AGI 3 leaderboard

Gemini 4 ArgonGemini 4 Argon - Provider Adapter

Verified scores

VariantARC-AGI-1ARC-AGI-2ARC-AGI-3(Standard harness)ARC-AGI-3(Provider Adapter harness)
High
98.5%
91.3%
—
97.3%
Medium
98.5%
87.1%
46.3%
97.3%
Low
76.5%
42.1%
49.8%
97.5%

Tasks & environments

Pass/fail per reasoning level across each benchmark.

ARC-AGI-3 Public Demo - Standard harness

25 environments

ARC-AGI-3 Public Demo - Provider Adapter harness

25 environments

ARC-AGI-2 Public Eval

120 tasks
Task
High
Medium
Low
✓✓✗
✓✓✓
✓✓✓
✓✗✗
✓✗✗
✓✓✗
✓✗✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✗✓✗
✓✗✗
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✗✗
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✗✗
✓✓✗
✓✗✗
✗✗✗
✓✓✗
✓✓✗
✓✗✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✗✗
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✗✗✗
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✗✗✗
✓✓✗
✓✓✗
✓✓✗
✗✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✓✗
✓✗✗
✓✓✗

ARC-AGI-1 Public Eval

400 tasks
Task
High
Medium
Low
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✗✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✗✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✗✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✓
✓✓✓
✓✗✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✓
✓✓✓
✓✓✓
✓✓✗
✓✓✗
✓✓✓
✓✓✗
✓✓✗