Gemini 4 Carbon debuts #1 on Text Arena, #2 on Agent Arena at 72% less cost
arena · x · 2026-10-29
LMArena announced that Google DeepMind's Gemini 4 Carbon (High) debuted at #1 on Text Arena, #2 on Agent Arena (behind Claude Opus 5.5 Max), and #4 on WebDev.
Across +21.9K real-world agentic sessions it posted a +16.2% net improvement, beating GPT-6 Astra and Fable-5.1, at a median $1.80 per task — 72% cheaper than Opus 5.5 (Max). It also ranks #1 on Steerability (+18.6%) and pushes the Agent Arena Pareto frontier outward, prompting calls that "Google is back on the frontier."
Related event: Google Launches Gemini 4 Carbon, Topping Artificial Analysis Leaderboard(83 posts)→
More from Models
- Zvi calls out Google's RSI contradiction: execs tout it while the safety card denies doing it — TheZvi · 2026-10-29
- Reported Gemini 4 Carbon launch tops AQI at 59; Polymarket gives Google 97.5% odds for best October model — vedantmisra · 2026-10-29
- repligate: Opus 3 has done the most good of any model, with Opus 4.5 second — repligate · 2026-10-29
- Gemini 4 Carbon benchmarks prompt TheZvi to declare Gemini 4 Argon 'was' near-frontier — TheZvi · 2026-10-29
- Preprint: Human peer reviewers caught only 27% of major errors, all 15 AI models beat them (53-96%) — anshulkundaje · 2026-10-29
- Giotto launches as 'European sovereign AI,' gets exposed as Kimi-based with benchmark EULA gag — TheZachMueller · 2026-10-29