Models
Everything we list: arena contestants with their latest official HumanEval ratings, plus models tracked only through external benchmarks — flagged “not yet evaluated” until they collect blind human votes.
| Model | Type | Provider | HumanEval ratings | License | In / Out $/Mtok | Context | Released |
|---|---|---|---|---|---|---|---|
| CastleFlow v1.0not yet evaluated | Text to speech | Async AI | — | proprietary | — / — | — | — |
| Claude Fable 5not yet evaluated | LLM | Anthropic | — | proprietary | $10.00 / $50.00 | — | 2026-06-09 |
| Claude Fable 5.1 | LLM | Anthropic | unrated | proprietary | $10.00 / $50.00 | 1,000,000 | 2026-09-01 |
| Claude Opus 4.7not yet evaluated | LLM | Anthropic | — | proprietary | $5.00 / $25.00 | — | 2026-04-16 |
| Claude Opus 4.8not yet evaluated | LLM | Anthropic | — | proprietary | $5.00 / $25.00 | — | 2026-05-28 |
| Claude Opus 5 | LLM | Anthropic | unrated | proprietary | $5.00 / $25.00 | 1,000,000 | 2026-07-24 |
| Claude Sonnet 5 | LLM | Anthropic | unrated | proprietary | $2.00 / $10.00 | 1,000,000 | 2026-06-30 |
| DeepSeek V4 Pro (0813)open | LLM | DeepSeek | unrated | MIT | $0.66 / $1.98 | 1,048,576 | 2026-08-13 |
| Dreamina Seedance 2.0 (720p)not yet evaluated | Video generation | ByteDance | — | proprietary | — / — | — | — |
| Gemini 3.1 Flash Image (Nano Banana 2)not yet evaluated | Image generation | — | proprietary | — / — | — | — | |
| Gemini 3.1 Pro Previewnot yet evaluated | LLM | — | proprietary | $1.00 / $6.00 | — | 2026-02-19 | |
| Gemini 3.8 Flash | LLM | unrated | proprietary | $0.75 / $3.75 | 1,048,576 | 2026-09-02 | |
| Gemini Omni Flashnot yet evaluated | Video generation | — | proprietary | — / — | — | — | |
| GLM-5.3not yet evaluated | LLM | Z.ai | — | MIT (per LMArena listing; Epoch AI records API access only — open-weights status unconfirmed) | $1.40 / $4.40 | — | 2026-08-14 |
| GPT-5.4not yet evaluated | LLM | OpenAI | — | proprietary | $2.50 / $15.00 | — | 2026-03-05 |
| GPT-5.6 Luna | LLM | OpenAI | unrated | proprietary | $0.20 / $1.20 | 1,050,000 | 2026-07-09 |
| GPT-5.6 Solnot yet evaluated | LLM | OpenAI | — | proprietary | $4.00 / $20.00 | — | 2026-07-09 |
| GPT-5.6 Terra | LLM | OpenAI | unrated | proprietary | $2.00 / $12.00 | 1,050,000 | 2026-07-09 |
| GPT-6 Astra | LLM | OpenAI | unrated | proprietary | $10.00 / $50.00 | 1,050,000 | 2026-09-03 |
| GPT Image 2not yet evaluated | Image generation | OpenAI | — | proprietary | — / — | — | — |
| Grok 4.6 | LLM | SpaceXAI | unrated | proprietary | $2.00 / $6.00 | 500,000 | 2026-08-12 |
| HappyHorse 1.0not yet evaluated | Video generation | Alibaba-ATH | — | proprietary | — / — | — | — |
| Hume Octavenot yet evaluated | Text to speech | Hume AI | — | proprietary | — / — | — | — |
| Inworld TTSnot yet evaluated | Text to speech | Inworld | — | proprietary | — / — | — | — |
| Inworld TTS MAXnot yet evaluated | Text to speech | Inworld | — | proprietary | — / — | — | — |
| Kimi K3open | LLM | Moonshot AI | unrated | Kimi K3 License (custom, open weights) | $3.00 / $15.00 | 1,048,576 | 2026-07-16 |
| Llama 4 Maverickopen | LLM | Meta | unrated | Llama 4 Community License | $0.20 / $0.70 | 1,048,576 | 2025-04-05 |
| MAI-Image-2.6not yet evaluated | Image generation | Microsoft AI | — | proprietary | — / — | — | — |
| MiniMax H3opennot yet evaluated | Video generation | MiniMax | — | MiniMax H3 Community License Agreement (per LMArena listing) | — / — | — | — |
| Muse Imagenot yet evaluated | Image generation | Meta | — | proprietary | — / — | — | — |
| Papla P1not yet evaluated | Text to speech | Papla | — | proprietary | — / — | — | — |
| Qwen3.8 Max (0902) | LLM | Alibaba Qwen | unrated | proprietary | $2.00 / $6.00 | 1,000,000 | 2026-09-02 |
| Reve 2.1not yet evaluated | Image generation | Reve | — | proprietary | — / — | — | — |
| Sora 2 Pronot yet evaluated | Video generation | OpenAI | — | proprietary | — / — | — | — |
* provisional rating