Unverified50% confidenceFactExact time
The Rocket Launcher team's tests were based on Claude Code version 2.1.293, with the environment reset before each run and each test run three times with the median taken.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/11/2026
First Seen
Valid until: 10/25/2026
Sources
Related Entities
Related Claims
UnverifiedThe 3.3x speedup test was run on July 7, with the baseline being ROCm 7.0 released in September 2024, the test build being a rockm.ai preview build running on 7.22 plus manual optimizations, running on 8 Instinct MI355X accelerators, and testing software that is not currently available for download.62% similarUnverifiedBullet 在 SWE-bench Verified 基准测试中取得 95.8% 的成绩，位列前三，平均每个任务耗时 119 秒60% similarUnverifiedOn a fixed revision of the repository, Praxa passed 1,027/1,027 unit tests and 89/89 Workerd tests, instrumented all 363 expected source files, and met four coverage lower bounds, though raw per-test records and independent reproduction are not yet available.59% similarUnverifiedIn benchmark tests, 2.0 shows notable improvements over the base model on IFBench (37.3→43.7), When2Call (48→58), and BFCL irrelevance (60→78).58% similarUnverifiedQwen3's 235B-parameter MoE flagship model approaches or surpasses closed-source top-tier models on multiple authoritative benchmarks.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996125API
curl https://kongchang.com/api/v1/knowledge/claims/996125MCP
get_claim(id=996125)