---
id: "2026-10-15-arc-agi-3-gemini-4-argon-97-5"
url: "https://postcutoff.com/e/2026-10-15-arc-agi-3-gemini-4-argon-97-5/"
as_of: "2026-10-20T02:15:00+02:00"
date: "2026-10-15"
date_precision: day
category: benchmark
importance: 4
confidence: high
status: [Confirmed]
sources: 9
editor: human editor
human_review: null
version: "2026-10-19"
---

As of: 2026-10-20 02:15 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-15-arc-agi-3-gemini-4-argon-97-5/

# ARC Prize verifies Gemini 4 Argon at 97.5% on ARC-AGI-3 with Google's harness (49.8% standard), the second lab above 95%

On Oct 15, 2026 ARC Prize published verified scores for Gemini 4 Argon: 97.5% on ARC-AGI-3 with the provider-adapter harness ($4.8K) and 49.8% with the standard harness ($5.8K), plus 91.3% on ARC-AGI-2 and 98.5% on ARC-AGI-1. Google DeepMind is the second lab, after OpenAI's GPT-6 Astra (99.9% / 62.7%), above 95% on ARC-AGI-3. The same week ARC Prize scored Haiku 5.5, DeepSeek V4.1 Flash and Reflection's Beam 1.0, and Tufa Labs reached 68.91% on the compute-limited Kaggle ARC-AGI-3 track.

## Key facts
- Gemini 4 Argon (ARC Prize, Oct 15): ARC-AGI-3 97.5% at $4.8K (provider-adapter harness, which preserves opaque reasoning and enables automatic compaction) and 49.8% at $5.8K (standard harness, low reasoning); ARC-AGI-2 91.3% at $0.32/task; ARC-AGI-1 98.5% at $0.16/task (~200k views on X)
- Caveat: API issues stopped complete standard-harness testing: low reasoning 49.8% (runs completed on 42 of 55 games), medium 46.3% (46 of 55), high only 19 of 55 so no score; scores count all 55 games with partial credit; costs use Argon's introductory $2/$10 per 1M tokens
- Comparison: GPT-6 Astra 99.9% (provider) / 62.7% (standard) on ARC-AGI-3 (Sept 3)
- Claude Haiku 5.5 (Oct 14): ARC-AGI-3 2.8% ($437, provider) and 0.5% ($388, standard); ARC-AGI-2 61.3% at $0.085/task; ARC-AGI-1 89.0% at $0.051/task; max reasoning omitted on ARC-AGI-2 after completing only 74 of 120 tasks
- DeepSeek V4.1 Flash (Oct 13): ARC-AGI-3 3.3% ($878, provider) and 0.9% ($1.2K, standard), the first model ARC Prize evaluated to exceed 3% on ARC-AGI-3 for under $1K total
- Reflection AI Beam 1.0 (Oct 19): ARC-AGI-2 23.5% at $0.61/task, ARC-AGI-1 74.0% at $0.31/task (xhigh reasoning; Baseten pricing $1.30/$4.30 per 1M); ARC-AGI-3 pending
- ARC Prize 2026 Kaggle (compute-limited): Tufa Labs set ARC-AGI-2 high score 88.06% (Oct 9; teams above 85% split a $150K bonus) and ARC-AGI-3 high score 68.91% (Oct 13, up from 56%)

## What happened

ARC Prize posted its verified evaluation of Gemini 4 Argon on Oct 15. With Google's own agent harness, Argon nearly matched GPT-6 Astra on
ARC-AGI-3, the interactive game benchmark launched in March 2026. With the neutral standard harness it reached about half, below Astra's
62.7%, though API failures left part of the standard runs unfinished. ARC Prize posted further verified results through the week. All
numbers here come from ARC Prize's own posts (read via fxtwitter); the result pages were not opened.

## Why it matters

Two frontier labs now score above 95% on ARC-AGI-3 when they control the harness, while open, compute-limited Kaggle entries passed
two-thirds. The gap between provider and standard harnesses (97.5% vs 49.8%) shows how much of agent performance on the benchmark
depends on scaffolding rather than the model alone.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 168 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 107 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 198 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 137 days after its cutoff

## Sources

1. [ARC Prize on X: Gemini 4 Argon on ARC-AGI (Verified), Oct 15](https://x.com/arcprize/status/2110768288523251762) (x.com, official)
2. [ARC Prize on X: Argon standard-harness API issues](https://x.com/arcprize/status/2110768292101042240) (x.com, official)
3. [ARC Prize: full Gemini 4 Argon results](https://arcprize.org/results/google-gemini-4-argon) (arcprize.org, official)
4. [ARC Prize on X: Haiku 5.5 on ARC-AGI (Verified), Oct 14](https://x.com/arcprize/status/2110417867288039864) (x.com, official)
5. [ARC Prize on X: DeepSeek V4.1 Flash on ARC-AGI-3, Oct 13](https://x.com/arcprize/status/2110060578530001231) (x.com, official)
6. [ARC Prize on X: Reflection Beam 1.0 on ARC-AGI (Verified), Oct 19](https://x.com/arcprize/status/2112230540283658499) (x.com, official)
7. [ARC Prize on X: Tufa Labs ARC-AGI-3 high score 68.91% (Oct 13)](https://x.com/arcprize/status/2110031207601979715) (x.com, official)
8. [ARC Prize on X: Tufa Labs ARC-AGI-2 high score 88.06% (Oct 9)](https://x.com/arcprize/status/2108578092558250148) (x.com, official)
9. [ARC Prize leaderboard](https://arcprize.org/leaderboard) (arcprize.org, official)

## Changes

- 2026-10-19 (filed): Created. Late; Haiku 5.5, DeepSeek V4.1 Flash, Beam 1.0 and Kaggle high scores added

## Related

- 2026-10-13: [Google releases Gemini 4 Argon broadly](https://postcutoff.com/e/2026-10-13-gemini-4-argon-general-availability/index.md)
- 2026-10-07: [Claude Haiku 5.5 released at $0.10/$0.50, matching GPT-6 Luna](https://postcutoff.com/e/2026-10-07-claude-haiku-5-5/index.md)
- 2026-10-05: [Reflection AI unveils Beam, a 501B-parameter Apache-2.0 open-weight MoE](https://postcutoff.com/e/2026-10-05-reflection-beam-501b-open-weight/index.md)
- 2026-10-01: [Open-source ARC-AGI-3 agents top out at 27.9% at ARC Prize 2026 Milestone #2](https://postcutoff.com/e/2026-10-01-arc-prize-2026-milestone-2-winners/index.md)
- 2026-09-30: [Google announces Gemini 4 Argon, its new frontier model, first released only to cyber defenders via the Fairwind Program](https://postcutoff.com/e/2026-09-30-gemini-4-argon/index.md)
- 2026-09-03: [GPT-6 Astra scores 62.7% on ARC-AGI-3, outacting humans on 96% of levels](https://postcutoff.com/e/2026-09-03-arc-agi-3-gpt-6-astra/index.md)
- Archived: 7 posts, listed in https://postcutoff.com/e/2026-10-15-arc-agi-3-gemini-4-argon-97-5/index.json