Artificial Analysis independently benchmarked Devin Fusion—the first multi-model coding agent on their Coding Agent Index. Claude Fable 5.1 (xhigh)+SWE-2 scores 62; GPT-6 Astra (xhigh)+SWE-2 scores 59 with ~43% lower cost and ~31% faster completion while retaining frontier-level performance.
Artificial Analysis (@ArtificialAnlys) published Meta Muse Spark 1.3 results on the Coding Agent Index in the Muse Code harness: the publicly available xhigh variant scores 64 (up 2 from Muse Spark 1.2 at 62) at about $1.72 per task—the cheapest agent above a 60 index score—while the partner-preview max variant scores 68, tied just behind Claude Opus 5 (xhigh) in Claude Code. Claude Fable 5.1 results are still pending.
Artificial Analysis (@ArtificialAnlys) shipped Intelligence Index v4.3: Terminal-Bench upgraded 2.1→4.0 (now mini-SWE-agent harness) and τ³-Banking replaced by AutomationBench-AA (657 private Zapier business workflows). Claude Fable 5.1 and GPT-6 Astra tie at 53; OpenAI holds most of the intelligence-vs-cost frontier across Astra reasoning efforts.
Artificial Analysis (@ArtificialAnlys) scored OpenBMB MiniCPM5-2B (2.6B dense, 131k context, Apache 2.0) at 15 on Intelligence Index v4.2 — highest among open-weights models under 4B total parameters. Strong small-model agentic results (GDPval-AA / τ³-Banking); coding/long-context benches like Terminal-Bench lag larger peers.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.