Alongside the Intelligence Index v5, Artificial Analysis is also launching a new Progress Index v1,...each version bump. The second new addition is Terminal-Bench-Science, a set of 70 agentic scientific research...the new Index, the cost of running a single Intelligence Index…
Claude Opus 5.5 scored 58 under the new methodology, edging out GPT-6 Astra's 57, while the best open-weight model, Kimi K3.1 Pro, trails by 12 points, four times the prior gap. Artificial Analysis rebuilt its widely-cited AI benchmark this week, putting 60% of the score behind…
models, inference, routers, harnesses & tools → 📈 GLM-5.3 vs. GLM 5.3 Flash on DeepSWE → 🚀 DeepSeek V4 Pro 0813 vs. GPT-5.6 Sol on DeepSWE → ⚡ On-demand B200s now available...Inference for custom models Explore the top open-source models Explore Top Open-Source Models Reliable GPU clusters at…
After a few months in the wilderness, Mistral appears to be leading the Western open model pack once again. Mistral’s newest flagship has landed on the Artificial Analysis Intelligence Index, and it’s enough to make it the highest-scoring...highest-scoring…
Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index Gemini 4 Carbon scores 59 on Intelligence Index v5, driven by leading performance in complex...leading in all…
rollout of its next-generation frontier model, Gemini 4 Carbon, Google has surged to the #1 spot on the newly updated Artificial Analysis Intelligence Index (v5.0), scoring an impressive 59 points....highlights a major shift in the AI landscape, with Gemini 4 Carbon leapfrogging competitors like…
Monhot AI's Kimi K3.1 Pro model scores higher than its predecessor and than GPT-6 Astra in AI benchmarks, while extra reasoning and tool calls can offset...lower token rates. Independent evaluator Artificial Analysis measured a jump from 13% for Kimi K3 to 67% for…
China’s DeepSeek has unveiled what it calls a faster and leaner version of its artificial intelligence model. DeepSeek added that this model employs “reinforcement learning...like game creation to 3D modeling. The new open-source model provides “substantial improvements across...the launch…
independent test is in, and it only half backs up Mistral’s claims: On Artificial Analysis, one of the most closely watched benchmarking services for A.I. models, Mistral Large 4 scores 38 points on the Intelligence Index. That makes it the strongest…
There is another major difference: availability. GPT-6 Astra and Claude Opus 5.5 are already available through production APIs and major enterprise platforms. Gemini 4 Argon is still being introduced through a phased...independent benchmark intelligence is the priority, Claude Opus 5.5 currently has…
The models developers build on: the OpenAI, Claude and Gemini developer platforms, open-weight models, new model releases and benchmarks.
An article joins this feed when it matches these terms. Each one is also a search of its own.