#评测/基准

Most AI benchmarks test retrieval — can a model find the known answer? However, the hardest problems in science require discovery, can a system earn an answer nobody has yet? Meet TRACES 🧭 — the world's first benchmark for measuring discoverative AI: AI that can work through evidence, test hypotheses, and reach verifiable conclusions on problems without answer keys. Proposed by our founder @tianqiao_chen, who defined its six capabilities. Three things published today: a definition of "discoverative intelligence", a rubric to tell sound investigation from lucky guesses, and a open call for both solvers and problems *Website: https://traces.apodex.com/

🥇 We evaluated Grok 4.6 on MedAgentBench, a benchmark for agentic clinical EHR tasks, and it took the top spot. Grok 4.6 posts the highest pass@1 we've measured to date, moving ahead of the previous leader, GPT-5.6 Sol, to claim first place on the leaderboard. 🏥 Grok 4.6 averages ~95.9% pass@1 (avg of 3 runs), edging out the prior best (GPT-5.6-sol at ~94.7%) and improving on Grok 4.5 by roughly 2.5 points. On a benchmark where the model acts as an autonomous agent in a simulated EHR, calling FHIR APIs to complete clinical tasks across 10 task types, the result is also remarkably consistent run to run (95.3% to 96.3%). 📊 Leaderboards: https://medicalsphere.ai/benchmarks

Uploading and logging into everything on OpenAI Finance is a better CPA and financial advisor than any human I’ve ever paid. Ditto contracts and lawyers, and results/scans and doctors. You only interface with humans out of the legacy capture and inertia of the offline world.

Agentic work is where @grok 4.6 lands hardest, taking the top spot on the Artificial Analysis Agentic Index at 59, tied with Claude Opus 5 Max. The index measures tool use, planning, autonomy and complex problem solving rather than single answers Grok 4.6 completes tasks in ~53 turns and ~0.5bn input tokens on average, against ~103 turns and ~2.0bn for Claude Opus 5 Max Cost of $0.84 per task, putting it on the intelligence versus cost per task Pareto frontier Enterprises buying agents pay per completed task, not per benchmark point. Turn efficiency is what determines whether a long-running workflow is affordable at volume. Two labs now sit at the top of this index with very different cost structures. Buyers get real choice on price for the first time in agentic deployment.

grok 4.6 vs gpt 5.6 sol – on three @gameofthrones castles two coding agents built three 3d castles from scratch in a single html file each, then had to render them in a real browser, prove the result with pixel measurements and fix what the numbers exposed before they were allowed to hand anything over the setup: each model in its own vendor cli – @spacexai's grok build, @openai's codex – both pointed at one @openrouter key. identical brief, identical reference image, identical verifier. no hints tasks: 1. castle black – the night's watch fort under the wall. a walled ward of black stone, a timber lift climbing 200m of ice, three arched openings with a braced gallery and an open riser stair, a mud yard. four reference photos, with one rule: open all four before writing code, open them again after every change, and follow the photo over our text wherever the two disagree 2. winterfell – an aerial snow diorama. twin curtain walls, drum towers, the godswood with the red weirwood, steam off the hot springs, day to night, and it has to stay smooth on a laptop 3. riverrun – the tully castle on its triangle between two rivers. coursed masonry with quoins, corbel tables under every parapet, conical roofs sitting on drum towers, true semicircular arches, and a button that floods the moat the binding rule: a verifier that opens the page in a real browser, collects every error and warning including shader compile failures, and measures the frame. zero errors, zero warnings, exposure proven by rgb numbers, every mode checked on its own. shipping unverified is a fail • total cost #1 grok 4.6 – $13.11 #2 gpt 5.6 sol – $20.18 • total build time #1 grok 4.6 – 129m 41s #2 gpt 5.6 sol – 149m 33s • total tokens #1 grok 4.6 – 19,951,587 #2 gpt 5.6 sol – 25,687,511 • model calls #1 grok 4.6 – 201 #2 gpt 5.6 sol – 338 • lines shipped #1 gpt 5.6 sol – 2,184 #2 grok 4.6 – 4,751 • how heavy the finished castles are, in polygons #1 grok 4.6 – 98k, 32k and 56k #2 gpt 5.6 sol – 148k, 144k and 104k observations: • all six builds passed with zero errors and zero warnings. the same brief without a verifier had produced a black screen from two one line shader mistakes, so the loop is doing the work here, not the model • grok ships lighter scenes and more code. castle black runs on 56k polygons against sol's 104k, out of a file carrying 1,672 lines against 640 • sol works in very small steps – 433 output tokens per call against grok's 1,706, and 338 calls against 201. on castle black it finally paid off: sol finished 5m 32s ahead • 93 to 98 percent of input tokens were cache reads. without prompt caching these runs cost about four times more, which is most of the economics of agentic coding right now follow @thehypedotnews for 24/7 ai news, analysis and breakdowns

Grok 4.6 just ranked #1 on CursorBench 3.2 Outperforming Claude Fable 5, Opus 5 and GPT-5.6 Sol on real-world coding performance And what makes this even crazier is the efficiency....the chart gives CursorBench performance against average cost per task, and Grok 4.6 is sitting right at the top of the frontier Grok 4.6 is insanely capable at coding....delivering frontier coding performance at ridiculous efficiency