Skip to content
Models
PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin Desktop: Continuity — 2026-10-31 Robinhood Ventures Fund I invests $10 million in Cognition, maker of D… Devin Desktop: Continuity — 2026-10-30 Cognition acquires Corridor for Devin Security boost Cognition releases FrontierCode 2.0 scores for Gemini 4 Carbon and Argon Cognition weighs new funding at $70‑80 B valuation Devin Desktop: Continuity — 2026-10-27 Cognition unveils FrontierCode 2.0 benchmark to test model judgment on… PLAN Free $0/mo PLAN Pro $20/mo PLAN Max $200/mo PLAN Teams $80/mo min + $40/seat Cognition FrontierCode (Oct 28) — score · cost per task Claude Opus 5.5 54.6% · $0.80/task Claude Fable 5 53.5% · $13.09/task Claude Opus 5 53.4% · $4.31/task GPT-6 Astra 53.3% · $4.59/task Claude Sonnet 5.5 52.1% · $1.59/task Claude Fable 5.1 50.9% · $3.28/task GPT-6.1 Sol 50.2% · $0.36/task SWE-2 50.0% · $1.18/task GPT-6 Sol 49.3% · $2.07/task Grok 4.6 48.0% · $2.88/task SWE-1.7 42.0% · $1.97/task SWE-1.6 9.4% · $0.49/task Devin Desktop: Continuity — 2026-10-31 Robinhood Ventures Fund I invests $10 million in Cognition, maker of D… Devin Desktop: Continuity — 2026-10-30 Cognition acquires Corridor for Devin Security boost Cognition releases FrontierCode 2.0 scores for Gemini 4 Carbon and Argon Cognition weighs new funding at $70‑80 B valuation Devin Desktop: Continuity — 2026-10-27 Cognition unveils FrontierCode 2.0 benchmark to test model judgment on…

Models · News

Cognition unveils FrontierCode 2.0 benchmark to test model judgment on underspecified prompts

Devin Central illustration
Devin Central illustration
The result is a benchmark that is far from saturated, with the top model scoring just 45%.

Cognition announced a new coding benchmark called FrontierCode 2.0 that evaluates a model’s ability to make judgments on underspecified prompts.

In a post on X, Cognition said FrontierCode 2.0 expands on the earlier version by including more diverse tasks, larger scopes and higher mergeability standards. The benchmark deliberately leaves engineering decisions ambiguous so models must demonstrate judgment beyond simply meeting a specification.

Cognition added that the benchmark is “far from saturated,” noting that the top‑performing model achieved a score of just 45 percent.

DevinAI, the official account for Cognition’s Devin platform, echoed the announcement, describing FrontierCode 2.0 as “our new coding benchmark that measures a model’s ability to go beyond the spec” and repeating the 45‑percent top score.

Sources

Fan coverage from Devin Central — not an official Cognition announcement. Devin is a trademark of Cognition.