Hermes 3 405B Instruct vs Ternary Bonsai 2 27BWhich Is Better in 2026?
Hermes 3 405B Instruct vs Ternary Bonsai 2 27B: which should you choose in 2026?
Hermes 3 405B Instruct (by Nous Research) and Ternary Bonsai 2 27B (by Prism ml) are compared below. Here is how they stack up on benchmarks, price, and capabilities, and which one to pick in 2026.
There are not enough shared, protocol-compatible benchmark results to declare a performance leader.
Ternary Bonsai 2 27B is about 5.5× cheaper on a blended 3:1 input/output basis ($0.18125 vs $1.00 per 1M tokens).
Ternary Bonsai 2 27B has the larger context window (262,144 tokens vs 131,072 tokens).
Choose Hermes 3 405B Instruct if…
- • your own prompt tests favor its output; shared comparable evidence does not identify a unique advantage
Choose Ternary Bonsai 2 27B if…
- • lower blended API cost matters for your workload
- • you work with longer documents, transcripts, or codebases
- • you need a model with explicit reasoning support
- • you need image inputs
The benchmark count includes only results measured with a matching benchmark version and protocol. Arena scores are shown separately. Missing, preliminary, and incompatible data is not treated as a controlled win. Published point-score comparisons are labeled separately when protocol details are incomplete. For text-output models, the verdict also compares token pricing and context windows.
Performance benchmarks
Every value links to its source. A dash means that no reviewed result is available for that exact model and protocol.
| Benchmark | Hermes 3 405B Instruct | Ternary Bonsai 2 27B |
|---|---|---|
A 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework. Guardrail-aware score | — | — |
A benchmark of difficult, verifiable information-seeking questions designed to measure an agent's ability to locate hard-to-find facts through web browsing. Accuracy | — | — |
A verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state. Mean task reward | — | — |
A human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests. Resolved | — | — |
Version 2.1 of the benchmark for completing realistic tasks in terminal environments. Harness, resource limits, and attempt count are part of the protocol. Mean task success | — | — |
A dynamic LLM evaluation framework in which models generate questions, answer them, and participate in reciprocal peer assessment. AutoBench is distinct from Zapier's AutomationBench. Weighted peer-assessment score | — | — |
The highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry. Accuracy | — | — |
A 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged. Accuracy | — | — |
Benchmark sources
Reviewed evidence last updated 2026-08-09.
Pricing, capabilities, and model facts
| Feature | Hermes 3 405B Instruct | Ternary Bonsai 2 27B |
|---|---|---|
| Context & model facts | ||
| Developer | Nous Research | Prism ml |
| API provider | Nous | PrismML |
| Input context | 131,072 tokens | 262,144 tokens |
| Maximum output | 16,384 tokens | 32,768 tokens |
| Released | — | — |
| Added to Writingmate | Aug 16, 2024 | Sep 18, 2026 |
| License | Not available | Not available |
| Knowledge cutoff | 2023-12-31 | — |
| Capabilities | ||
| Inputs | Text | Text, Image |
| Outputs | Text | Text |
| Provider endpoint accepts tool parameters | No | Yes |
| Reasoning | No | Yes |
| Vision | No | Yes |
| Image Generation | No | No |
| Video Generation | No | No |
| API pricing | ||
| Input (per 1M tokens) | $1.00 | $0.075 |
| Output (per 1M tokens) | $1.00 | $0.50 |
| Blended 3:1 input/output | $1.00 | $0.18125 |
| API performance | ||
| p95 latency | Not measured | Not measured |
| Output throughput | Not measured | Not measured |
| Writingmate shows API performance only when both models have enough observations from the same measurement window, prompt profile, and provider. Third-party latency values are not copied into this table. | ||
Data sources
- Writingmate model catalog (pricing, limits, and availability)
Catalog data last updated Sep 18, 2026.
Why Pay for Multiple Subscriptions?
Comparing Hermes 3 405B Instruct from Nous Research with Ternary Bonsai 2 27B from Prism ml? Instead of managing separate API keys and subscriptions, get both with Writingmate.
| Plan | Price | Hermes 3 405B Instruct | Ternary Bonsai 2 27B | AI Images | AI Video |
|---|---|---|---|---|---|
Writingmate Pro Most popular | $20/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Writingmate Ultimate Power users | $60/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Hermes 3 405B Instruct vs Ternary Bonsai 2 27B FAQ
Which is better, Hermes 3 405B Instruct or Ternary Bonsai 2 27B?
There are not enough shared, protocol-compatible benchmark results to declare a performance leader. Ternary Bonsai 2 27B is about 5.5× cheaper on a blended 3:1 input/output basis ($0.18125 vs $1.00 per 1M tokens). Ternary Bonsai 2 27B has the larger context window (262,144 tokens vs 131,072 tokens).
Which model is cheaper to use through an API?
Ternary Bonsai 2 27B is about 5.5× cheaper on a blended 3:1 input/output basis ($0.18125 vs $1.00 per 1M tokens).
Which model supports more context?
Ternary Bonsai 2 27B has the larger context window (262,144 tokens vs 131,072 tokens).
Can I switch between Hermes 3 405B Instruct and Ternary Bonsai 2 27B?
Yes. Use the model selector on this page to open any current Writingmate model comparison. You can also run the same prompt with both models in Writingmate.
Related comparisons
More Hermes 3 405B Instruct comparisons
GLM 5.3 FlashX
Z.AI
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s.
Pareto
Unbiased
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
Schematron V2 Turbo
Inference net
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net.
Schematron V2 Small
Inference net
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.
Fugu Ultra v2
Sakana AI
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.
Fugu Max
Sakana AI
Fugu Max is the cost-performance model in Sakana AI's Fugu family.
More Ternary Bonsai 2 27B comparisons
GLM 5.3 FlashX
Z.AI
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s.
Fugu Ultra v2
Sakana AI
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.
Fugu Max
Sakana AI
Fugu Max is the cost-performance model in Sakana AI's Fugu family.
Ling 3.0 Flash VL
inclusionAI
Ling 3.0 Flash VL is a model by inclusionAI.
DeepSeek V4.1 Flash
DeepSeek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
Qwen3.8 Max (0902)
Qwen
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.