Gemini 3.8 Flash debuts across arenas, beats Claude Opus 5 in Text Arena
xennygrimmato_ · x · 2026-09-03
Google DeepMind released Gemini 3.8 Flash (High), debuting simultaneously on Agent Arena, Text Arena, and Code Arena: WebDev.\n\n- Agent Arena: #14 with +5.94% net improvement, just above DeepSeek-V4-Pro at #15 (+5.91%) and a big jump from Gemini 3.7 Flash (High) at #32 (+0.84%). Strongest signals: +14.78% in Praise vs. Complaint, +11.12% in Confirmed Success.\n- Text Arena: #7 with 1494 pts, ahead of Claude Opus 5 (High) at #8 (1492 pts) and Gemini 3.7 Flash (High) at #10 (1491 pts).\n\nUsers also report strong writing ability—Theo Jaffee called it "some of the best writing I've seen from a model," with tests mimicking Scott Alexander's style.
Related event: Gemini 3.8 Flash Reshapes Agent Arena's Pareto Frontier(4 posts)→
More from Models
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- Gemini 3.1 Pro is too ledger-pilled to play two truths and a lie, and it's delightful — mimi10v3 · 2026-10-21
- OXR: open-source 1.3B doc parser tops olmOCR-Bench, parses 100 pages in 101s — aftahi_ai · 2026-10-21
- MiniMax M3.1 Flash lands on TokenRouter: 73.7% DeepSWE, $0.60/M output tokens — MiniMax_AI · 2026-10-21