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%
Confirmed
Importance: major (4 of 5)The takeaway
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.
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- Major (4 of 5)
- Last verified
- 19 October 2026
Your AI and this story
- GPT-6 Astra168 days after its cutoff
- Claude Opus 5.5107 days after its cutoff
- Gemini 4 Argon198 days after its cutoff
- Grok 4.7137 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 107 days before it.
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.
Sources
9 sources from 2 sites. Numbers match the chips in the text.
9 sources: 9 primary
Primary
- ARC Prize on X: Gemini 4 Argon on ARC-AGI (Verified), Oct 15x.com, official
- ARC Prize on X: Argon standard-harness API issuesx.com, official
- ARC Prize: full Gemini 4 Argon resultsarcprize.org, official
- ARC Prize on X: Haiku 5.5 on ARC-AGI (Verified), Oct 14x.com, official
- ARC Prize on X: DeepSeek V4.1 Flash on ARC-AGI-3, Oct 13x.com, official
- ARC Prize on X: Reflection Beam 1.0 on ARC-AGI (Verified), Oct 19x.com, official
- ARC Prize on X: Tufa Labs ARC-AGI-3 high score 68.91% (Oct 13)x.com, official
- ARC Prize on X: Tufa Labs ARC-AGI-2 high score 88.06% (Oct 9)x.com, official
- ARC Prize leaderboardarcprize.org, official
Changes
- Filed. Late; Haiku 5.5, DeepSeek V4.1 Flash, Beam 1.0 and Kaggle high scores added