Google Ledger: Codex Pass@1 Rises 3.4% on SWE-Bench - blockchain.news
Google Ledger: Codex Pass@1 Rises 3.4% on SWE-Bench blockchain.news
Topics: Benchmarks
Entities: BenchmarksGoogle
Source feed
11 items
Google Ledger: Codex Pass@1 Rises 3.4% on SWE-Bench blockchain.news
Topics: Benchmarks
Entities: BenchmarksGoogle
AI Trading Agents Benchmark Released by Dolores Research Coinfomania
Topics: Benchmarks
Entities: Benchmarks
Dolores Research launches WAGMI Bench, an open-source benchmark for AI trading agents on Virtuals Protocol Crypto Briefing
Topics: Benchmarks
Entities: Benchmarks
Agent Lightning Reports a 14.6-Point SWE-bench Gain quasa.io
Topics: Benchmarks
Entities: Benchmarks
GPT-5.6 Sol vs Qwen3.8 Max vs Opus 4.6: SWE-Bench Pro tech-insider.org
Topics: Benchmarks
Entities: Benchmarks
EP82: Claude Mythos / Fable 5 RELEASED -- Anthropic's New Frontier AI (Deep Dive, 80% SWE-Bench) Christine Lagarde (0crRCso3o2) Mshale
Topics: Benchmarks
Entities: AnthropicClaudeBenchmarksMythos
SWE-Bench Is Getting Replaced??? Mohammad Abbas (MAGjnsqzHW) Mshale
Topics: Benchmarks
Entities: Benchmarks
Claude Opus 4.8 Is Here — 88.6% SWE-bench, 3x Cheaper Fast Mode Gloucester Debenhams Skeleton Discovery (9S3XFfnWoe) Mshale
Topics: Benchmarks
Entities: ClaudeClaude OpusBenchmarks
Claude Code vs Cursor 2026: 80.8% SWE-bench, 1M Context [Tested] tech-insider.org
Topics: Benchmarks
Entities: ClaudeBenchmarksClaude CodeCursor
Claude Opus 4.7 Boosts SWE-bench to 87.6% blockchain.news
Topics: Benchmarks
Entities: ClaudeClaude OpusBenchmarks
Scale Labs debuts new Refactoring Leaderboard for AI TestingCatalog AI News
Topics: Benchmarks
Entities: Benchmarks