GPT-6.1 Sol from @OpenAI on ARC-AGI (Verified):
- ARC-AGI-3: 52.7%, $7.6K (standard harness), 96.4%, $4.4K (provider adapter harness)
- ARC-AGI-2: 94.2%, $0.25/task
- ARC-AGI-1: 98.5%, $0.06/task
Its 96.4% on v3 was comparable to GPT-6 Astra's 99.9% but at a 77% lower cost.
Sep 30, 2026 · 8:18 PM UTC
37
68
1,148
135,138
On ARC-AGI-2, GPT-6.1 Sol's best score of 94.2% was comparable to GPT-6 Astra's 95.0%, also at a 77% lower cost.
Full results: arcprize.org/results/openai-…
1
4
83
7,825
Like GPT-6 Astra, GPT-6.1 Sol made better decisions at higher reasoning levels on ARC-AGI-3, requiring fewer actions to complete levels, which reduced the total inference cost.
For example, on sk48 using the provider adapter (which preserves opaque reasoning state between turns and enables auto compaction), GPT-6.1 Sol with max reasoning worked out how to reposition the colored blocks around an obstacle sooner, while low spent much longer revisiting blocked moves and testing controls that didn't help. That helped it complete the game in 463 actions versus 1,078 with low reasoning.
Watch the replay: arcprize.org/replay/c299de73…
1
1
55
6,548
- Leaderboard: arcprize.org/leaderboard
- Reproduce the public results: github.com/arcprize/arc-agi-…
- Testing policy: arcprize.org/policy
- Full GPT-6.1 Sol results: arcprize.org/results/openai-…
20
4,029
