Best AI models for Hermes

#1 on Chatbot Arena with 1,504 Elo — the highest score of any publicly available model. Leads instruction-following, long-form work, and agentic tasks. The thinking variant pushes even further. Slower than Sonnet but makes fewer mistakes on genuinely hard problems. Use it for your most important work.

#4 on Chatbot Arena (1,492 Elo), #1 on GPQA Diamond reasoning (94.1%), and #1 on creative writing Arena scores. Exceptional value — at $2/$12 per 1M tokens it matches or beats models costing 4–10x more. The 2M context variant handles entire codebases and book-length documents. Currently in preview.

OpenAI's flagship released March 2026. Leads SWE-bench Pro coding (57.7%) and Terminal-Bench DevOps (75.1%). Solid GPQA Diamond (91.67%). The 1.1M token context window is among the largest of any frontier model, and it costs less per token than Opus. Best pick when you need breadth across coding, writing, and reasoning at a reasonable price.

The fast, smart everyday workhorse. 87.5% on GPQA Diamond, 79.6% on SWE-bench Verified, 1,462 Elo on Chatbot Arena. Nearly as capable as Opus at lower cost and higher speed. The right choice for high-volume tasks — daily summaries, coding, research — where you need quality without always paying Opus prices.

The remarkable open-source value pick. Released December 2025 with MIT license and "reasoning-first" architecture that integrates thinking directly into tool use. Claims GPT-5 level performance at a tiny fraction of the cost. Self-hostable. Arena score of 1,424 puts it solidly in reach of the closed frontier. The budget pick that doesn't embarrass itself against anything.

Leads EQ-Bench Creative Writing at 1,936 Elo — higher than Opus (1,932) on the benchmark specifically designed to resist sycophancy and measure genuine literary quality. Best voice consistency over long documents: tone, register, and style stay coherent across sessions. At 85% lower cost than Opus, it's the smart pick for high-volume writing — drafts, summaries, long-form content pipelines.

Leads the Mazur creative writing benchmark (8.53) and instruction-following Arena (1,500 Elo — highest of any model tested). The thinking variant (8.56 Mazur) pushes further for complex literary work. #1 on Chatbot Arena overall at 1,504 Elo. Best for projects demanding deep voice and stylistic range — where spending more per token is justified by the work's importance.

#1 on Chatbot Arena creative writing Elo (1,487) — human raters prefer it for fiction and blogs — and best for AI-tell avoidance across independent evals. The 2M context and 65K output limit are unmatched for long-form projects: entire chapters, full reports, long narrative arcs. Strong multilingual creative writing in 40+ languages. 12x cheaper on input than Opus.

Solid for structured and commercial writing: technical docs, reports, pitch decks, email campaigns. Excellent instruction-following (~92% IFEval). Ranked ~9th on Arena creative writing — noticeably behind Claude and Gemini for fiction and literary prose, but a strong default when your output needs precise formatting or structured argument flow over stylistic voice.

~1,700 EQ-Bench Creative Writing Elo — roughly 87% of Sonnet's literary quality at 80% lower cost. The budget pick for high-volume content: product descriptions, social copy, blog drafts, content pipelines where you need coherent writing at scale without paying frontier prices on every call. API is live and available now.

Leads GPQA Diamond at 94.1% and ARC-AGI-2 visual reasoning at 77.1% — the highest score on both of the hardest published reasoning benchmarks. Near-perfect AIME 2025 math (98%+). Strong across physics, chemistry, biology, and multi-domain expert knowledge. The 2M context makes it uniquely capable for research requiring both depth and breadth in one pass.

~92% on GPQA Diamond, 41.6% on Humanity's Last Exam, and ~92% on IFEval strict compliance. The best-balanced reasoning model: strong on scientific knowledge, reliable at following precise analytical instructions, and capable across coding and writing tasks simultaneously. The GPT-5.4 Pro variant adds extended reasoning for the genuinely hard problems.

89.2% GPQA Diamond and #1 on Chatbot Arena overall (1,504 Elo). Best for long-context reasoning tasks requiring both analytical depth and 1M-token coherence — feeding in entire research corpora, reviewing large codebases, or synthesising book-length material. Claude Sonnet 4.6 leads GDPval-AA structured knowledge retrieval (1,633 Elo #1) if throughput and cost matter.

89.8% on GPQA Diamond at just $0.50/$3 per 1M tokens — the best reasoning value by a large margin, outperforming models that cost 20x more. The thinking mode shows its chain-of-thought for auditing. 0.34s time-to-first-token. If you run many hard reasoning calls per day and can't justify frontier pricing, nothing else comes close at this price point.

88.2% on GPQA Diamond with a 1M token context window at a fraction of frontier pricing — a genuine dark-horse for knowledge work. Strong on structured knowledge retrieval and multi-step analytical tasks. The same model that leads Terminal-Bench for coding also performs well on reasoning benchmarks, making it unusually versatile. Available via Alibaba Cloud and OpenRouter.