Artificial Analysis
AdoptPlatforms
A benchmarking and comparison source for model performance and pricing.
Why it's here
Placed in Adopt: 19 article(s) of evidence from 5 source(s), led by model releases, with 5 in the last 30 days. Confidence 90%.
Evidence (16)
- 4Hacker News·9/24/2026framework_updateDaily LLM value frontier by budget
This page tracks large language models by comparing performance against blended price per 1M tokens, highlighting the best option for each budget and the runner-up. It is updated daily from Artificial Analysis data and shows changes such as new models, removals, and re-scored or re-priced entries.
- 8The New Stack·9/23/2026model_releaseXiaomi opens MiMo-V2.6 with public RL training
Xiaomi unveiled MiMo-V2.6, a large open-weight model with multimodal support, a one-million-token context window, and claimed frontier-level performance on coding, agentic, cybersecurity, and research tasks. The company also publicized its reinforcement-learning training run, released the weights under the MIT license, and shared a smaller Qwen-based model for further agentic RL research.
- 6The New Stack·9/22/2026model_releaseClaude Opus 5.5 ranked top on Artificial Analysis
Artificial Analysis published an evaluation of Anthropic's Claude Opus 5.5 reasoning model, placing it first on its Intelligence Index among 212 models. The report says the model supports text and image input, has a 1M-token context window, and is relatively expensive at $4 per 1M input tokens and $20 per 1M output tokens.
- 7Hacker News·9/22/2026model_releaseXiaomi MiMo-V2.6-Pro Analysis
Artificial Analysis published a benchmark, pricing, and performance review of Xiaomi's MiMo-V2.6-Pro open-weights model. The report says the model ranks highly on intelligence, supports text, image, speech, and video input with a 1M-token context window, but is slower than average and somewhat verbose.
- 7Ars Technica AI·9/15/2026researchOpen AI models nearly match frontier models at much lower cost
A Mozilla report says the performance gap between frontier AI models from US companies and top open-weights models from Chinese companies has narrowed to 4.4 months. It also finds that open models are often the better default for routine work, while closed frontier models mainly justify their premium for expert work, long-context tasks, and heavy retrieval.
- 7Hacker News·9/5/2026framework_updateArtificial Analysis updates Intelligence Index v4.2
Artificial Analysis has released Intelligence Index v4.2, adding more complex benchmark tasks, private held-out test sets, and grading improvements to reduce gaming. The update introduces AA-Briefcase and GDP.pdf, while also reweighting the index and highlighting new leaderboard results led by Anthropic and OpenAI.
- 9InfoQ·9/3/2026model_releaseOpenAI Posts System Card for GPT-6 Astra
OpenAI has published a system card for GPT-6 Astra, outlining safety, capability, and deployment considerations for the model. The Hacker News discussion highlights reported gains on ARC-AGI-3 and the Artificial Analysis Coding Agent Index, indicating strong interest in its performance and safety profile.
- 6Hacker News·9/2/2026model_releaseMultiverse launches Quasar 438B reasoning model for agents
Multiverse Computing has launched Quasar 438B, a compressed 438-billion-parameter reasoning model aimed at coding and enterprise agents. The company says the model is fast and efficient, but key details about its compression method, hardware requirements, and real-world agent performance remain unclear.
- 7The New Stack·9/1/2026model_releaseMeta launches Muse Voice Transcribe for real-time speech recognition
Meta has released Muse Voice Transcribe, a real-time speech recognition model that it says outperforms comparable systems on several benchmarks, including English streaming transcription and speaker identification. The model supports more than 70 languages, long conversations, and is available through Meta’s API and apps, though Meta is not releasing open weights.
- 7Hacker News·8/21/2026researchThe Cost of LLM Intelligence Has Fallen 100x
The article argues that progress in large language models is not only about higher peak capability, but also about making useful capability far cheaper. It cites benchmarking data showing that the cost of a given intelligence level has dropped sharply, with one frontier-level capability tier falling from $1.22 per task in February to $0.022 today, and suggests this makes high-volume AI workflows newly practical.
- 7The New Stack·8/20/2026model_releaseUpstage launches Solar Pro 4 for reliable AI agent workflows
Upstage AI has launched Solar Pro 4, a closed commercial LLM positioned around agent reliability, long-context reasoning, document understanding, and tool use in production workflows. The company says the model is designed to reduce retries, malformed outputs, and token waste, and reports strong early usage and benchmark results alongside integrations with OpenRouter and Hermes Agent.
- 5Hacker News·8/18/2026researchGLM-5.3 Scores Strong on Artificial Analysis Benchmarks
Artificial Analysis published benchmark results for GLM-5.3 (max), a proprietary reasoning model with a 1M-token context window. It ranks highly on intelligence, runs faster than average, and is priced in the mid-range for comparable models, though it is notably verbose.
- 6Simon Willison·8/17/2026breakthroughQwen 3.8 27B reaches 52 on Artificial Analysis index
Simon Willison highlights that Qwen 3.8 27B scored 52 on the Artificial Analysis Intelligence Index. He notes this matches GPT-5.6 Luna (max) and trails GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max) by one point, despite Qwen being only 27B parameters.
- 8Hacker News·8/12/2026model_releaseGrok 4.6 reaches AI index frontier at lower cost
Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index, tying the GPT-5.6 Sol max score and narrowing the gap to the top frontier models. It also shows strong agentic performance across knowledge work, banking, and terminal benchmarks while keeping pricing at $2/$6 per million input/output tokens.
- 6Hacker News·8/6/2026researchQwen3.8 Max tops Artificial Analysis's agentic index
Artificial Analysis updated its Intelligence Index to v4.1.1 and published a new evaluation for Qwen3.8 Max. The model is now ranked as the best overall on the agentic index, based on the site's independent benchmark suite. The update also includes methodology changes and refreshed scores for other models, but the headline result is Qwen3.8 Max moving to the top of the ranking.
- 5Hacker News·7/31/2026model_releaseDeepSeek V4 Flash 0731 ranks highly in model analysis
Artificial Analysis reports that DeepSeek V4 Flash 0731 (Reasoning, Max Effort) scores strongly on its Intelligence Index, placing it among the leading open-weight models in its size class. The model has a 1M-token context window, 13B active parameters out of 284B total, and relatively low input/output pricing compared with peers.