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 — 2026-11-07 Devin offers 50% off Teams plan for users migrating from competing cod… Cognition launches SWE-2 Flash, a faster, cheaper coding model for Dev… Devin Review 2.0 cuts PR review cost by 82%, pricing at $0.25‑$0.75 pe… Cognition closes $400 M round at $10.2 B valuation, two months after W… Cognition publishes 30‑day security checklist after series of high‑pro… Devin rolls out hierarchical budgets for granular enterprise AI spend … Devin Desktop: Continuity — 2026-10-31 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 — 2026-11-07 Devin offers 50% off Teams plan for users migrating from competing cod… Cognition launches SWE-2 Flash, a faster, cheaper coding model for Dev… Devin Review 2.0 cuts PR review cost by 82%, pricing at $0.25‑$0.75 pe… Cognition closes $400 M round at $10.2 B valuation, two months after W… Cognition publishes 30‑day security checklist after series of high‑pro… Devin rolls out hierarchical budgets for granular enterprise AI spend … Devin Desktop: Continuity — 2026-10-31

Models · News

Cognition releases FrontierCode 2.0 scores for Gemini 4 Carbon and Argon

Devin Central graphic
Devin Central graphic
Gemini 4 Carbon scores near SOTA with a score of 40% and a cost of $4.04 per task

Cognition posted FrontierCode 2.0 benchmark results for Google’s Gemini 4 Carbon and Argon models on Oct. 30. The scores measure each model’s ability to go beyond the specification in coding tasks.

According to Cognition, Gemini 4 Carbon achieved a score of 40% with a cost of $4.04 per task, placing it behind Claude Opus 5.5, GPT‑6 Astra and Claude Sonnet 5.5. Gemini 4 Argon recorded a 26.3% score at $6.41 per task, ahead of Muse Wonder 1.0 but trailing Claude Haiku 5.5 and Grok 4.7.

The company provided a leaderboard link for the full set of scores.

Cognition’s release suggests the Gemini models are narrowing the performance gap with other top‑tier offerings in the FrontierCode 2.0 coding benchmark.

Sources

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