Xiaomi MiMo-V2.6-Flash hits Agent Arena Pareto frontier at $0.04 per task
arena · x · 2026-10-02
Agent Arena reports Xiaomi's MiMo-V2.6-Flash landed on the agent Pareto frontier with -0.57% net improvement at a $0.04 median cost per task. Top of the frontier: Claude Fable 5.1 (Max) at +14.55% ($4.50/task), Claude Opus 5.5 (High) at +13.78% ($1.56/task), GPT 6 Sol (Max) at +10.65% ($0.90/task), Gemini 4 Argon at +7.92%, and open-weight entries from Tencent (Hy4 preview), DeepSeek V4.1 Flash (+4.01%, $0.09/task) and MiMo V2.6 Pro. Rankings draw on 2M+ real agent sessions across 48 models.
More from Models
- Nat Eliason suspects @bot now runs on 4.7, says he reaches for Claude and Codex less — nateliason · 2026-10-02
- Users report queries being routed to Fable 5.5, with SVG tests said to far beat 5.1 — kimmonismus · 2026-10-02
- 180B Qwen model runs on one DGX Spark: 2.39-bit quant keeps 95.5% of BF16 scores — TheZachMueller · 2026-10-02
- Grok 4.7 reportedly live across all modes in the Grok app — XFreeze · 2026-10-02
- Claude's cloud sessions don't cost extra — bonus credits are cloud-only tokens — stablequan · 2026-10-02
- One 'please continue' Prompt Burned a 5-Hour Usage Cap in 6.5 Minutes — thawingfrog · 2026-10-02